{"slug": "muse-spark", "name": "Muse Spark", "category": "ai", "category_name": "AI models and assistants", "description": "Meta's large language model, usable via API and coding tools such as OpenCode.", "recommenders": 14, "commenters": 21, "warners": 1, "score": 13.898, "rising": 10.02, "first": "2026-04-08", "latest": "2026-10-15", "why": "Liked as a cheap, fast model for coding agents that some commenters rate near Opus or Sonnet tier and use for checking code against specs.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 14, "neutral": 4, "compare": 3, "warn": 1}, "spark": [0, 0, 0, 0, 0, 2, 0, 0, 1, 2, 7, 2], "listed": true, "loved": ["Coding ability", "Price"], "caveat": "Data training", "short_quote": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great.", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "freemium", "aliases": ["Muse Spark", "Muse Spark 1.3", "Muse Spark 1.2"], "verdict": [{"text": "Liked as a cheap, fast model for coding agents", "cites": [{"id": 794774432, "item_id": 49673402, "url": "https://news.ycombinator.com/item?id=49673402", "by": "sourcecodeplz", "date": "2026-09-12", "stance": "recommend", "quote": "unbeatable price/intel ratio per M tokens:", "excerpt": "Muse Spark 1.3 Contribs unbeatable price/intel ratio per M tokens: $0.10 (input) $0.20 (output) $0.002 (cached-input)", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 801733696, "item_id": 50108356, "url": "https://news.ycombinator.com/item?id=50108356", "by": "sejje", "date": "2026-10-15", "stance": "recommend", "quote": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great.", "excerpt": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great. Speaks nicely, great at driving linux. Not frontier-level coding, but comparable to luna, deepseek. It was amazing for the price.", "context": "", "use_case": "agentic coding, driving Linux", "switched_from": "", "story": "Muse Spark Open"}]}, {"text": " that some commenters rate near Opus or Sonnet tier and use for checking code against specs.", "cites": [{"id": 793927568, "item_id": 49620473, "url": "https://news.ycombinator.com/item?id=49620473", "by": "willsmith72", "date": "2026-09-09", "stance": "recommend", "quote": "First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "excerpt": "I agree, and stay away from meta generally in life wherever possible That said, I've got more time for projects this week so flew through my Claude max plan. Now I'm trying muse spark 1.3 with opencode which is free with pretty generous usage allowance. First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "context": "ran out of Claude max plan usage", "use_case": "coding with opencode", "switched_from": "Claude", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 796988001, "item_id": 49811750, "url": "https://news.ycombinator.com/item?id=49811750", "by": "sieve", "date": "2026-09-23", "stance": "recommend", "quote": "perfectly capable of following my spec and then poking holes in the implementation", "excerpt": "I used to read the code till around May. Now I don't. Instead I validate behavior. And have multiple LLMs verify that the code implements my handwritten spec. MiMo 2.5/2.6, MuseSpark 1.3, DeepSeek V4/4.1 Flash and GLM 5.3 Flash are perfectly capable of following my spec and then poking holes in the implementation till there are none left.", "context": "validates behavior instead of reading code", "use_case": "spec implementation and verification", "switched_from": "", "story": "GPT-6 Sol and Luna"}]}, {"text": " The most common caveat is that the cheap contributor tier shares your data with Meta for training,", "cites": [{"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 800200945, "item_id": 50012559, "url": "https://news.ycombinator.com/item?id=50012559", "by": "robertlane0", "date": "2026-10-08", "stance": "recommend", "quote": "the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me", "excerpt": "Honestly for me the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me, especially on a $10 OpenCode Go sub, with the caveat that everything I use it on is open source which makes the fact that I'm sharing it with Meta a little moot because it's already published permissively on GitHub anyways.", "context": "works only on open source code", "use_case": "open source coding", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 787024384, "item_id": 49189024, "url": "https://news.ycombinator.com/item?id=49189024", "by": "ray_kay777", "date": "2026-08-05", "stance": "recommend", "quote": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training", "excerpt": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training - judging by the AA benchmarks it seems like overall cost per task is similar to the new Deepseek Flash but with better benchmarks (and inbuilt vision capabilities).", "context": "", "use_case": "personal work, low cost per task", "switched_from": "", "story": "Muse Code and Muse Spark 1.2"}, {"id": 792679041, "item_id": 49542440, "url": "https://news.ycombinator.com/item?id=49542440", "by": "MangoCoffee", "date": "2026-09-02", "stance": "neutral", "quote": "its free on opencode and i use it for personal projects", "excerpt": ">I started using Spark 1.2 for development because if you're willing to let Meta train on your data it was dirt cheap its free on opencode and i use it for personal projects. most of my personal projects are AI generated since its personal projects. nothing important are on them. it is hilarious if Meta is training their AI model with AI generated code.", "context": "", "use_case": "personal projects", "switched_from": "", "story": "Muse Spark 1.3"}]}, {"text": " and one user found its generated code and reviews poor, with mostly hallucinated issues.", "cites": [{"id": 796994080, "item_id": 49812130, "url": "https://news.ycombinator.com/item?id=49812130", "by": "slopinthebag", "date": "2026-09-23", "stance": "warn", "quote": "the code it generated, while technically working, was entirely garbage", "excerpt": "shocking. the code it generated, while technically working, was entirely garbage. i used it for code review and it flagged twenty issues, sol checked the review and found 75% of them were hallucinations. sol was much closer to reality. i no longer trust benchmarks at all because of it.", "context": "", "use_case": "code generation and review", "switched_from": "", "story": "GPT-6 Sol and Luna"}]}], "praise": [{"label": "Coding ability", "summary": "Commenters say it works well for coding agents, with some calling it close to Opus tier.", "quotes": [{"id": 793927568, "item_id": 49620473, "url": "https://news.ycombinator.com/item?id=49620473", "by": "willsmith72", "date": "2026-09-09", "stance": "recommend", "quote": "First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "excerpt": "I agree, and stay away from meta generally in life wherever possible That said, I've got more time for projects this week so flew through my Claude max plan. Now I'm trying muse spark 1.3 with opencode which is free with pretty generous usage allowance. First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "context": "ran out of Claude max plan usage", "use_case": "coding with opencode", "switched_from": "Claude", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 796988001, "item_id": 49811750, "url": "https://news.ycombinator.com/item?id=49811750", "by": "sieve", "date": "2026-09-23", "stance": "recommend", "quote": "perfectly capable of following my spec and then poking holes in the implementation", "excerpt": "I used to read the code till around May. Now I don't. Instead I validate behavior. And have multiple LLMs verify that the code implements my handwritten spec. MiMo 2.5/2.6, MuseSpark 1.3, DeepSeek V4/4.1 Flash and GLM 5.3 Flash are perfectly capable of following my spec and then poking holes in the implementation till there are none left.", "context": "validates behavior instead of reading code", "use_case": "spec implementation and verification", "switched_from": "", "story": "GPT-6 Sol and Luna"}]}, {"label": "Price", "summary": "Commenters cite a very low per-token price and say it is worth it for the cost.", "quotes": [{"id": 794774432, "item_id": 49673402, "url": "https://news.ycombinator.com/item?id=49673402", "by": "sourcecodeplz", "date": "2026-09-12", "stance": "recommend", "quote": "unbeatable price/intel ratio per M tokens:", "excerpt": "Muse Spark 1.3 Contribs unbeatable price/intel ratio per M tokens: $0.10 (input) $0.20 (output) $0.002 (cached-input)", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 801733696, "item_id": 50108356, "url": "https://news.ycombinator.com/item?id=50108356", "by": "sejje", "date": "2026-10-15", "stance": "recommend", "quote": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great.", "excerpt": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great. Speaks nicely, great at driving linux. Not frontier-level coding, but comparable to luna, deepseek. It was amazing for the price.", "context": "", "use_case": "agentic coding, driving Linux", "switched_from": "", "story": "Muse Spark Open"}, {"id": 800200945, "item_id": 50012559, "url": "https://news.ycombinator.com/item?id=50012559", "by": "robertlane0", "date": "2026-10-08", "stance": "recommend", "quote": "the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me", "excerpt": "Honestly for me the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me, especially on a $10 OpenCode Go sub, with the caveat that everything I use it on is open source which makes the fact that I'm sharing it with Meta a little moot because it's already published permissively on GitHub anyways.", "context": "works only on open source code", "use_case": "open source coding", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}, {"label": "Free access", "summary": "Users report free or generous access through OpenCode Zen and OpenCode Go.", "quotes": [{"id": 793927568, "item_id": 49620473, "url": "https://news.ycombinator.com/item?id=49620473", "by": "willsmith72", "date": "2026-09-09", "stance": "recommend", "quote": "First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "excerpt": "I agree, and stay away from meta generally in life wherever possible That said, I've got more time for projects this week so flew through my Claude max plan. Now I'm trying muse spark 1.3 with opencode which is free with pretty generous usage allowance. First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "context": "ran out of Claude max plan usage", "use_case": "coding with opencode", "switched_from": "Claude", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 792702225, "item_id": 49543889, "url": "https://news.ycombinator.com/item?id=49543889", "by": "superfrank", "date": "2026-09-02", "stance": "neutral", "quote": "I use it through Opencode Go", "excerpt": "Funny. I use it through Opencode Go which gives more use than I can use, but didn't realize it was actually free on Zen. Will switch to that I guess", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 792679041, "item_id": 49542440, "url": "https://news.ycombinator.com/item?id=49542440", "by": "MangoCoffee", "date": "2026-09-02", "stance": "neutral", "quote": "its free on opencode and i use it for personal projects", "excerpt": ">I started using Spark 1.2 for development because if you're willing to let Meta train on your data it was dirt cheap its free on opencode and i use it for personal projects. most of my personal projects are AI generated since its personal projects. nothing important are on them. it is hilarious if Meta is training their AI model with AI generated code.", "context": "", "use_case": "personal projects", "switched_from": "", "story": "Muse Spark 1.3"}]}, {"label": "Reasoning and vision", "summary": "Testers say it solved a floor-plan PDF task and common gotcha prompts that other models missed.", "quotes": [{"id": 763164800, "item_id": 47697800, "url": "https://news.ycombinator.com/item?id=47697800", "by": "laser", "date": "2026-04-08", "stance": "recommend", "quote": "it knocked it out of the park, extracted and displayed the pertinent pages from a multi-page PDF inline in the chat and rendered a correct answer.", "excerpt": "First thing I tried is a visual reasoning test on floor plan documents that applies directly to something I'm working on and needed that I posed to ChatGPT, Claude, Gemini, and Grok yesterday (lowest tier paid plans on each). In that test only Gemini succeeded while the other models hallucinated/incorrectly reported the relative location of building units. I just posed the identical prompt/document to Muse Spark and ", "context": "", "use_case": "visual reasoning on floor plans", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}, {"id": 763109152, "item_id": 47694322, "url": "https://news.ycombinator.com/item?id=47694322", "by": "eranation", "date": "2026-04-08", "stance": "recommend", "quote": "tried it (with instant mode), it's an impressive model.", "excerpt": "Sarcasm aside, tried it (with instant mode), it's an impressive model. It nailed all the ChatGPT meme gotchas (walk to the carwash, Alice 50 brothers, upside down cup, R's in strawberry, which number is bigger, 9.11 or 9.9?) I guess all that money poaching OpenAI / Anthropic talent went somewhere... Now, would I use \"Meta Muse Code\" or \"Muse CoWork\" if I have to have a facebook account to all of my developers? Maybe ", "context": "", "use_case": "general chat model", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}, {"id": 787024384, "item_id": 49189024, "url": "https://news.ycombinator.com/item?id=49189024", "by": "ray_kay777", "date": "2026-08-05", "stance": "recommend", "quote": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training", "excerpt": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training - judging by the AA benchmarks it seems like overall cost per task is similar to the new Deepseek Flash but with better benchmarks (and inbuilt vision capabilities).", "context": "", "use_case": "personal work, low cost per task", "switched_from": "", "story": "Muse Code and Muse Spark 1.2"}]}, {"label": "Speed", "summary": "Users describe it as very fast, at over 200 tokens per second.", "quotes": [{"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 792664720, "item_id": 49541545, "url": "https://news.ycombinator.com/item?id=49541545", "by": "WASDx", "date": "2026-09-02", "stance": "recommend", "quote": "it has been quite good and fast", "excerpt": "I'm party using 1.2 to reverse engineer and re-implement an old game binary and it has been quite good and fast. The contributor pricing is very attractive, excited to try 1.3 and see if I feel a difference. 1.2 can get stuck outputting similar sounding thought summaries with no apparent progress when asked to solve bugs. Then I've switched to GLM-5.3-Flash which for this use case has been clearly better at finding s", "context": "", "use_case": "reverse engineering an old game binary", "switched_from": "", "story": "Muse Spark 1.3"}]}, {"label": "Writing Latin", "summary": "One learner says it is among the best models for writing Latin.", "quotes": [{"id": 792703760, "item_id": 49543985, "url": "https://news.ycombinator.com/item?id=49543985", "by": "coolcoder613", "date": "2026-09-02", "stance": "recommend", "quote": "I find it's one of the best at it, alongside Gemini.", "excerpt": "I have not tried Muse Spark for code, but I've been using it for a while to write Latin. I find it's one of the best at it, alongside Gemini. For example, I've recently been using it to translate the subtitles of the show I'm watching into Latin, to provide me with a bit more input. (I'm learning Latin, for context)", "context": "learning Latin", "use_case": "writing and translating Latin", "switched_from": "", "story": "Muse Spark 1.3"}]}], "caveats": [{"label": "Data training", "summary": "The cheap contributor tier shares your data with Meta for training.", "quotes": [{"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 800200945, "item_id": 50012559, "url": "https://news.ycombinator.com/item?id=50012559", "by": "robertlane0", "date": "2026-10-08", "stance": "recommend", "quote": "the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me", "excerpt": "Honestly for me the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me, especially on a $10 OpenCode Go sub, with the caveat that everything I use it on is open source which makes the fact that I'm sharing it with Meta a little moot because it's already published permissively on GitHub anyways.", "context": "works only on open source code", "use_case": "open source coding", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 787024384, "item_id": 49189024, "url": "https://news.ycombinator.com/item?id=49189024", "by": "ray_kay777", "date": "2026-08-05", "stance": "recommend", "quote": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training", "excerpt": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training - judging by the AA benchmarks it seems like overall cost per task is similar to the new Deepseek Flash but with better benchmarks (and inbuilt vision capabilities).", "context": "", "use_case": "personal work, low cost per task", "switched_from": "", "story": "Muse Code and Muse Spark 1.2"}]}, {"label": "Code quality", "summary": "Some users rank it below frontier models or DeepSeek Flash, and one found its reviews were mostly hallucinated.", "quotes": [{"id": 796994080, "item_id": 49812130, "url": "https://news.ycombinator.com/item?id=49812130", "by": "slopinthebag", "date": "2026-09-23", "stance": "warn", "quote": "the code it generated, while technically working, was entirely garbage", "excerpt": "shocking. the code it generated, while technically working, was entirely garbage. i used it for code review and it flagged twenty issues, sol checked the review and found 75% of them were hallucinations. sol was much closer to reality. i no longer trust benchmarks at all because of it.", "context": "", "use_case": "code generation and review", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 801733696, "item_id": 50108356, "url": "https://news.ycombinator.com/item?id=50108356", "by": "sejje", "date": "2026-10-15", "stance": "recommend", "quote": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great.", "excerpt": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great. Speaks nicely, great at driving linux. Not frontier-level coding, but comparable to luna, deepseek. It was amazing for the price.", "context": "", "use_case": "agentic coding, driving Linux", "switched_from": "", "story": "Muse Spark Open"}, {"id": 791954241, "item_id": 49497140, "url": "https://news.ycombinator.com/item?id=49497140", "by": "sieve", "date": "2026-08-30", "stance": "compare", "quote": "I would rank MS 1.2 below it.", "excerpt": "I have used all three extensively. DS4 Flash is quite smart. I would rank MS 1.2 below it. MiMo is the dumbest of them all but good enough for basic stuff. MiMo wins handsomely if you want to think about your code for minutes at a time as you write. I use it to make changes as I think. I know it will screw up some stuff. I then switch to MS/DS4 once every few hours and have it do a code review and fix the broken stuf", "context": "", "use_case": "code review and fixes", "switched_from": "", "story": "Hy4 preview"}]}, {"label": "Debugging loops", "summary": "Version 1.2 could get stuck repeating thought summaries without progress on bugs.", "quotes": [{"id": 792664720, "item_id": 49541545, "url": "https://news.ycombinator.com/item?id=49541545", "by": "WASDx", "date": "2026-09-02", "stance": "recommend", "quote": "it has been quite good and fast", "excerpt": "I'm party using 1.2 to reverse engineer and re-implement an old game binary and it has been quite good and fast. The contributor pricing is very attractive, excited to try 1.3 and see if I feel a difference. 1.2 can get stuck outputting similar sounding thought summaries with no apparent progress when asked to solve bugs. Then I've switched to GLM-5.3-Flash which for this use case has been clearly better at finding s", "context": "", "use_case": "reverse engineering an old game binary", "switched_from": "", "story": "Muse Spark 1.3"}]}, {"label": "Integration quirks", "summary": "Its server-side tool calling caused a bug when used with Codex.", "quotes": [{"id": 781629248, "item_id": 48851828, "url": "https://news.ycombinator.com/item?id=48851828", "by": "weitendorf", "date": "2026-07-09", "stance": "recommend", "quote": "also a very cool model that I'm enjoying using so far!", "excerpt": "Just got it working with codex in a container! FYI I think there is a bug most others will run into at the Codex:Muse interface. It's some kind of parsing or integration error due to what I think is codex not anticipating server-side tool calling and how meta treats those ids... first couple times running codex with muse, it would fail on its first non-web search call. Got it fixed, not personally sold on the bespoke", "context": "", "use_case": "model used via Codex", "switched_from": "", "story": "Introducing Muse Spark 1.1"}]}, {"label": "Meta account", "summary": "One commenter disliked needing a Facebook account for Meta's coding products.", "quotes": [{"id": 763109152, "item_id": 47694322, "url": "https://news.ycombinator.com/item?id=47694322", "by": "eranation", "date": "2026-04-08", "stance": "recommend", "quote": "tried it (with instant mode), it's an impressive model.", "excerpt": "Sarcasm aside, tried it (with instant mode), it's an impressive model. It nailed all the ChatGPT meme gotchas (walk to the carwash, Alice 50 brothers, upside down cup, R's in strawberry, which number is bigger, 9.11 or 9.9?) I guess all that money poaching OpenAI / Anthropic talent went somewhere... Now, would I use \"Meta Muse Code\" or \"Muse CoWork\" if I have to have a facebook account to all of my developers? Maybe ", "context": "", "use_case": "general chat model", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}]}], "who": [{"by": "robertlane0", "context": "works only on open source code", "url": "https://news.ycombinator.com/item?id=50012559", "date": "2026-10-08"}, {"by": "sieve", "context": "validates behavior instead of reading code", "url": "https://news.ycombinator.com/item?id=49811750", "date": "2026-09-23"}, {"by": "willsmith72", "context": "ran out of Claude max plan usage", "url": "https://news.ycombinator.com/item?id=49620473", "date": "2026-09-09"}, {"by": "coolcoder613", "context": "learning Latin", "url": "https://news.ycombinator.com/item?id=49543985", "date": "2026-09-02"}], "tags": ["for coding agents", "via OpenCode", "for budget-conscious devs", "for personal projects", "for language learning"], "use_cases": ["coding", "agentic coding, driving linux", "open source coding", "code generation and review", "spec implementation and verification", "coding with opencode"], "compared": [{"slug": "opencode", "name": "OpenCode", "co": 7, "switched_from": 0, "switched_to": 0}, {"slug": "glm-flash", "name": "GLM Flash", "co": 3, "switched_from": 0, "switched_to": 1}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 2, "switched_from": 1, "switched_to": 0}, {"slug": "chatgpt", "name": "ChatGPT", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "grok", "name": "Grok", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gemini", "name": "Gemini", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49541256", "title": "Muse Spark 1.3", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=50107379", "title": "Muse Spark Open", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49805509", "title": "GPT-6 Sol and Luna", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49672966", "title": "Ask HN: What default model do you use and why?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49615537", "title": "Muse \u2013 Meta\u2019s personal AI agent", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49187575", "title": "Muse Code and Muse Spark 1.2", "mentions": 2}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 2}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {"recommend": 2, "compare": 2}, "2026-09": {"recommend": 7, "neutral": 4, "warn": 1}, "2026-10": {"recommend": 2, "compare": 1}}, "quotes": [{"id": 801752546, "item_id": 50109534, "url": "https://news.ycombinator.com/item?id=50109534", "by": "alexpotato", "date": "2026-10-15", "stance": "compare", "quote": "I think Muse Spark 1.3 is better but GLM 5.3 Flash is an excellent daily driver.", "excerpt": "Been using GLM 5.3 Flash via Ollama Cloud basic subscription: if this is the only model I had to use for the rest of my life, I would be cool with that. It's good at a wide variety of tasks including reverse engineering, design, working with ESP 32 etc. I think Muse Spark 1.3 is better but GLM 5.3 Flash is an excellent daily driver.", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark Open"}, {"id": 801733696, "item_id": 50108356, "url": "https://news.ycombinator.com/item?id=50108356", "by": "sejje", "date": "2026-10-15", "stance": "recommend", "quote": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great.", "excerpt": "I used spark 1.3 extensively in prime-agent (a pi derivative) and I thought it was great. Speaks nicely, great at driving linux. Not frontier-level coding, but comparable to luna, deepseek. It was amazing for the price.", "context": "", "use_case": "agentic coding, driving Linux", "switched_from": "", "story": "Muse Spark Open"}, {"id": 800206722, "item_id": 50012920, "url": "https://news.ycombinator.com/item?id=50012920", "by": "robertlane0", "date": "2026-10-08", "stance": "recommend", "quote": "I'm not sure I'll be compelled enough to switch from Muse Spark 1.3", "excerpt": "Well, according to Artificial Analysis (which I'll admit I've been using as a bit of a mental crutch to avoid comparing models myself, so YMMV), it's smarter and slightly cheaper than Gemini 3.8 Flash, which has been my benchline for \"cheap and smart enough\", I'll give it a try on OpenCode for the week but I'm not sure I'll be compelled enough to switch from Muse Spark 1.3.", "context": "", "use_case": "", "switched_from": "", "story": "Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter"}, {"id": 800200945, "item_id": 50012559, "url": "https://news.ycombinator.com/item?id=50012559", "by": "robertlane0", "date": "2026-10-08", "stance": "recommend", "quote": "the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me", "excerpt": "Honestly for me the intelligence gap between DS 4.1 Flash and Muse Spark 1.3 makes Muse more worth it for me, especially on a $10 OpenCode Go sub, with the caveat that everything I use it on is open source which makes the fact that I'm sharing it with Meta a little moot because it's already published permissively on GitHub anyways.", "context": "works only on open source code", "use_case": "open source coding", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 796994080, "item_id": 49812130, "url": "https://news.ycombinator.com/item?id=49812130", "by": "slopinthebag", "date": "2026-09-23", "stance": "warn", "quote": "the code it generated, while technically working, was entirely garbage", "excerpt": "shocking. the code it generated, while technically working, was entirely garbage. i used it for code review and it flagged twenty issues, sol checked the review and found 75% of them were hallucinations. sol was much closer to reality. i no longer trust benchmarks at all because of it.", "context": "", "use_case": "code generation and review", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 796988001, "item_id": 49811750, "url": "https://news.ycombinator.com/item?id=49811750", "by": "sieve", "date": "2026-09-23", "stance": "recommend", "quote": "perfectly capable of following my spec and then poking holes in the implementation", "excerpt": "I used to read the code till around May. Now I don't. Instead I validate behavior. And have multiple LLMs verify that the code implements my handwritten spec. MiMo 2.5/2.6, MuseSpark 1.3, DeepSeek V4/4.1 Flash and GLM 5.3 Flash are perfectly capable of following my spec and then poking holes in the implementation till there are none left.", "context": "validates behavior instead of reading code", "use_case": "spec implementation and verification", "switched_from": "", "story": "GPT-6 Sol and Luna"}, {"id": 794842180, "item_id": 49677636, "url": "https://news.ycombinator.com/item?id=49677636", "by": "ricardobeat", "date": "2026-09-12", "stance": "neutral", "quote": "Adding Muse Spark 1.3 to that mix but not convinced yet.", "excerpt": "Opus 5 at low effort is quite good at most tasks, and will go a long way even on the base plan. At higher thinking levels it is unbearably cautious and verbose - it drives me mad. I don\u2019t have a use for Fable at current prices. My current go-tos are DS Flash, Minimax M3 for subagents. Adding Muse Spark 1.3 to that mix but not convinced yet.", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794774432, "item_id": 49673402, "url": "https://news.ycombinator.com/item?id=49673402", "by": "sourcecodeplz", "date": "2026-09-12", "stance": "recommend", "quote": "unbeatable price/intel ratio per M tokens:", "excerpt": "Muse Spark 1.3 Contribs unbeatable price/intel ratio per M tokens: $0.10 (input) $0.20 (output) $0.002 (cached-input)", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 793927568, "item_id": 49620473, "url": "https://news.ycombinator.com/item?id=49620473", "by": "willsmith72", "date": "2026-09-09", "stance": "recommend", "quote": "First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "excerpt": "I agree, and stay away from meta generally in life wherever possible That said, I've got more time for projects this week so flew through my Claude max plan. Now I'm trying muse spark 1.3 with opencode which is free with pretty generous usage allowance. First time I've been impressed by meta's AI products. It feels not far below opus 4.8ish", "context": "ran out of Claude max plan usage", "use_case": "coding with opencode", "switched_from": "Claude", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 793861616, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "recommend", "quote": "the thing flies, it's a pleasure to use", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 792742048, "item_id": 49546378, "url": "https://news.ycombinator.com/item?id=49546378", "by": "goatydev", "date": "2026-09-03", "stance": "recommend", "quote": "I used 1.2 for free for a while, and it was a pretty good experience.", "excerpt": "I used 1.2 for free for a while, and it was a pretty good experience. 1.3 would also be worth using, provided the price is reasonable.", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 792710113, "item_id": 49544382, "url": "https://news.ycombinator.com/item?id=49544382", "by": "dv35z", "date": "2026-09-03", "stance": "neutral", "quote": "You can check out Muse Spark 1.3 by using OpenCode", "excerpt": "You can check out Muse Spark 1.3 by using OpenCode (https://opencode.ai/ - open-source AI / coding harness). There's a terminal version and a GUI / desktop version. Good luck!", "context": "", "use_case": "", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 792703760, "item_id": 49543985, "url": "https://news.ycombinator.com/item?id=49543985", "by": "coolcoder613", "date": "2026-09-02", "stance": "recommend", "quote": "I find it's one of the best at it, alongside Gemini.", "excerpt": "I have not tried Muse Spark for code, but I've been using it for a while to write Latin. I find it's one of the best at it, alongside Gemini. For example, I've recently been using it to translate the subtitles of the show I'm watching into Latin, to provide me with a bit more input. (I'm learning Latin, for context)", "context": "learning Latin", "use_case": "writing and translating Latin", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 792702225, "item_id": 49543889, "url": "https://news.ycombinator.com/item?id=49543889", "by": "superfrank", "date": "2026-09-02", "stance": "neutral", "quote": "I use it through Opencode Go", "excerpt": "Funny. I use it through Opencode Go which gives more use than I can use, but didn't realize it was actually free on Zen. Will switch to that I guess", "context": "", "use_case": "coding", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 792679041, "item_id": 49542440, "url": "https://news.ycombinator.com/item?id=49542440", "by": "MangoCoffee", "date": "2026-09-02", "stance": "neutral", "quote": "its free on opencode and i use it for personal projects", "excerpt": ">I started using Spark 1.2 for development because if you're willing to let Meta train on your data it was dirt cheap its free on opencode and i use it for personal projects. most of my personal projects are AI generated since its personal projects. nothing important are on them. it is hilarious if Meta is training their AI model with AI generated code.", "context": "", "use_case": "personal projects", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 792664720, "item_id": 49541545, "url": "https://news.ycombinator.com/item?id=49541545", "by": "WASDx", "date": "2026-09-02", "stance": "recommend", "quote": "it has been quite good and fast", "excerpt": "I'm party using 1.2 to reverse engineer and re-implement an old game binary and it has been quite good and fast. The contributor pricing is very attractive, excited to try 1.3 and see if I feel a difference. 1.2 can get stuck outputting similar sounding thought summaries with no apparent progress when asked to solve bugs. Then I've switched to GLM-5.3-Flash which for this use case has been clearly better at finding s", "context": "", "use_case": "reverse engineering an old game binary", "switched_from": "", "story": "Muse Spark 1.3"}, {"id": 791954241, "item_id": 49497140, "url": "https://news.ycombinator.com/item?id=49497140", "by": "sieve", "date": "2026-08-30", "stance": "compare", "quote": "I would rank MS 1.2 below it.", "excerpt": "I have used all three extensively. DS4 Flash is quite smart. I would rank MS 1.2 below it. MiMo is the dumbest of them all but good enough for basic stuff. MiMo wins handsomely if you want to think about your code for minutes at a time as you write. I use it to make changes as I think. I know it will screw up some stuff. I then switch to MS/DS4 once every few hours and have it do a code review and fix the broken stuf", "context": "", "use_case": "code review and fixes", "switched_from": "", "story": "Hy4 preview"}, {"id": 787915184, "item_id": 49244699, "url": "https://news.ycombinator.com/item?id=49244699", "by": "mark_l_watson", "date": "2026-08-10", "stance": "recommend", "quote": "Meta is rocking AI. As of last week I have been using their excellent muse coding harness with their model Muse Spark 1.2.", "excerpt": "Meta is rocking AI. As of last week I have been using their excellent muse coding harness with their model Muse Spark 1.2. Starting this morning I am running their new local 30B model muse-glimmer on my old MacMini 32G using Ollama (remember to increase the context size!) and pi coding harness. I am getting good results with muse-glimmer running locally, with the caveat that everything runs slowly (e.g., give it a ta", "context": "", "use_case": "coding", "switched_from": "", "story": "Meta Muse Glimmer \u2013 open weights 30B local coding model"}, {"id": 787207186, "item_id": 49200449, "url": "https://news.ycombinator.com/item?id=49200449", "by": "phoghed", "date": "2026-08-06", "stance": "compare", "quote": "it would be nice to know how it compares on a cost/performance basis against models in its class.", "excerpt": "Not really. I use Luna plenty and if this model is available in GH Copilot it would be nice to know how it compares on a cost/performance basis against models in its class.", "context": "", "use_case": "", "switched_from": "", "story": "Muse Code and Muse Spark 1.2"}, {"id": 787024384, "item_id": 49189024, "url": "https://news.ycombinator.com/item?id=49189024", "by": "ray_kay777", "date": "2026-08-05", "stance": "recommend", "quote": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training", "excerpt": "This makes it a very interesting alternative to Deepseek for personal work where I don't care about the training - judging by the AA benchmarks it seems like overall cost per task is similar to the new Deepseek Flash but with better benchmarks (and inbuilt vision capabilities).", "context": "", "use_case": "personal work, low cost per task", "switched_from": "", "story": "Muse Code and Muse Spark 1.2"}, {"id": 781629248, "item_id": 48851828, "url": "https://news.ycombinator.com/item?id=48851828", "by": "weitendorf", "date": "2026-07-09", "stance": "recommend", "quote": "also a very cool model that I'm enjoying using so far!", "excerpt": "Just got it working with codex in a container! FYI I think there is a bug most others will run into at the Codex:Muse interface. It's some kind of parsing or integration error due to what I think is codex not anticipating server-side tool calling and how meta treats those ids... first couple times running codex with muse, it would fail on its first non-web search call. Got it fixed, not personally sold on the bespoke", "context": "", "use_case": "model used via Codex", "switched_from": "", "story": "Introducing Muse Spark 1.1"}, {"id": 763164800, "item_id": 47697800, "url": "https://news.ycombinator.com/item?id=47697800", "by": "laser", "date": "2026-04-08", "stance": "recommend", "quote": "it knocked it out of the park, extracted and displayed the pertinent pages from a multi-page PDF inline in the chat and rendered a correct answer.", "excerpt": "First thing I tried is a visual reasoning test on floor plan documents that applies directly to something I'm working on and needed that I posed to ChatGPT, Claude, Gemini, and Grok yesterday (lowest tier paid plans on each). In that test only Gemini succeeded while the other models hallucinated/incorrectly reported the relative location of building units. I just posed the identical prompt/document to Muse Spark and ", "context": "", "use_case": "visual reasoning on floor plans", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}, {"id": 763109152, "item_id": 47694322, "url": "https://news.ycombinator.com/item?id=47694322", "by": "eranation", "date": "2026-04-08", "stance": "recommend", "quote": "tried it (with instant mode), it's an impressive model.", "excerpt": "Sarcasm aside, tried it (with instant mode), it's an impressive model. It nailed all the ChatGPT meme gotchas (walk to the carwash, Alice 50 brothers, upside down cup, R's in strawberry, which number is bigger, 9.11 or 9.9?) I guess all that money poaching OpenAI / Anthropic talent went somewhere... Now, would I use \"Meta Muse Code\" or \"Muse CoWork\" if I have to have a facebook account to all of my developers? Maybe ", "context": "", "use_case": "general chat model", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}]}