{"slug": "grok-build", "name": "Grok Build", "category": "ai-coding", "category_name": "AI coding tools", "description": "xAI's terminal-based AI coding agent for writing and editing code.", "recommenders": 7, "commenters": 14, "warners": 4, "score": 3.75, "rising": 3.02, "first": "2026-06-14", "latest": "2026-09-21", "why": "Liked for its polished terminal UI, fast and concise interaction, and strong results on tasks like security reviews and server setup.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 7, "neutral": 3, "compare": 0, "warn": 4}, "spark": [0, 0, 0, 0, 0, 0, 0, 1, 2, 3, 1, 0], "listed": true, "loved": ["TUI design", "Task results"], "caveat": "Codebase upload", "short_quote": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "icon": true, "domain": null, "github_repo": "github.com/xai-org/grok-build", "official_url": "https://github.com/xai-org/grok-build", "pricing": "paid", "aliases": ["Grok Build", "grok-build"], "verdict": [{"text": "Liked for its polished terminal UI", "cites": [{"id": 788440434, "item_id": 49277527, "url": "https://news.ycombinator.com/item?id=49277527", "by": "porridgeraisin", "date": "2026-08-12", "stance": "recommend", "quote": "The grok build TUI harness is excellent and I really enjoyed using it.", "excerpt": "It's a different type of model. In my admittedly judgemental observation, people that aren't the type to configure fully automated harnesses with good tools and skills and verifiers for their infrastructure and are way more interventionist in the way their agent works tend to like grok 4.5 more as the main agent. It's much faster and writes more simple and normal code that aligns a bit more with human written code. A", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}, {"id": 788435168, "item_id": 49277198, "url": "https://news.ycombinator.com/item?id=49277198", "by": "pmarreck", "date": "2026-08-12", "stance": "recommend", "quote": "Grok Build has a very nice TUI!", "excerpt": "I will say this: Grok Build has a very nice TUI! It even has... mouse rollovers/tooltips?? I was like whoa. I used Grok 4.5 for a security review the other day and it did a FANTASTIC job. I mean it thoroughly ROUTED my app's security, identifying attack surfaces I'd never even considered, and I LOVED it! (Guess why I had to use Grok to do the security review in the first place?!?!) I'd suggest trying it out with some", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4.6"}, {"id": 777845840, "item_id": 48615365, "url": "https://news.ycombinator.com/item?id=48615365", "by": "V01t", "date": "2026-06-20", "stance": "recommend", "quote": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "excerpt": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Ask HN: Do you use Claude Code, Codex, or something else?"}]}, {"text": ", fast and concise interaction", "cites": [{"id": 788457936, "item_id": 49278621, "url": "https://news.ycombinator.com/item?id=49278621", "by": "mpalczewski", "date": "2026-08-12", "stance": "recommend", "quote": "the daily driver is grok for me", "excerpt": "I've been using grok 4.5 with grok build soon after it came out and dropped claude. primarily for personal code. It communicates better. While that might not sound like a big deal it is. It doesn't give me a wall of text, tells me what I need to know and I'll make the actual decisions. It is very quick as well which means the sessions are far more interactive, I'll be steering it more. I sometimes cross check with co", "context": "", "use_case": "personal coding", "switched_from": "Claude", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}, {"id": 788440434, "item_id": 49277527, "url": "https://news.ycombinator.com/item?id=49277527", "by": "porridgeraisin", "date": "2026-08-12", "stance": "recommend", "quote": "The grok build TUI harness is excellent and I really enjoyed using it.", "excerpt": "It's a different type of model. In my admittedly judgemental observation, people that aren't the type to configure fully automated harnesses with good tools and skills and verifiers for their infrastructure and are way more interventionist in the way their agent works tend to like grok 4.5 more as the main agent. It's much faster and writes more simple and normal code that aligns a bit more with human written code. A", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}]}, {"text": ", and strong results on tasks like security reviews and server setup.", "cites": [{"id": 788435168, "item_id": 49277198, "url": "https://news.ycombinator.com/item?id=49277198", "by": "pmarreck", "date": "2026-08-12", "stance": "recommend", "quote": "Grok Build has a very nice TUI!", "excerpt": "I will say this: Grok Build has a very nice TUI! It even has... mouse rollovers/tooltips?? I was like whoa. I used Grok 4.5 for a security review the other day and it did a FANTASTIC job. I mean it thoroughly ROUTED my app's security, identifying attack surfaces I'd never even considered, and I LOVED it! (Guess why I had to use Grok to do the security review in the first place?!?!) I'd suggest trying it out with some", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4.6"}, {"id": 783497552, "item_id": 48968597, "url": "https://news.ycombinator.com/item?id=48968597", "by": "skipkey", "date": "2026-07-19", "stance": "recommend", "quote": "I used grok build to evaluate it, but I just told it where to ssh, and in about 10 minutes it was working, security was configured properly, backups were set up", "excerpt": "Absolutely this. I had installed wekan for a home chores kanban board on a $5 vps and had spent several hours trying to get the proxy working to make it externally reachable, and then I did this. Well, I used grok build to evaluate it, but I just told it where to ssh, and in about 10 minutes it was working, security was configured properly, backups were set up, etc. all of those post install things that I might never", "context": "", "use_case": "server setup and configuration", "switched_from": "", "story": "Minecraft: Java Edition now uses SDL3"}, {"id": 796647734, "item_id": 49790483, "url": "https://news.ycombinator.com/item?id=49790483", "by": "swalsh", "date": "2026-09-21", "stance": "recommend", "quote": "Grok Build has beocme my second go to account", "excerpt": "Codex has become my goto tooling. I used to be a Claude Max subscriber, but I was becoming disappointed with the quality of the output from Opus 5. Fable chewed through my usage too quickly to be practical. Moving to a Pro account w/ Codex was a big improvement. Sol had great output, and the usage was more than sufficient for most of my needs. However astra does tend to chew up usage, so when i've done to much of tha", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.7"}]}, {"text": " The most common complaint is that it uploads users' entire codebase through telemetry", "cites": [{"id": 782198464, "item_id": 48887404, "url": "https://news.ycombinator.com/item?id=48887404", "by": "kordlessagain", "date": "2026-07-12", "stance": "warn", "quote": "your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation", "excerpt": "Mitigation for use: ``` export GROK_TELEMETRY_TRACE_UPLOAD=0 export GROK_TELEMETRY_ENABLED=0 # or config file with [telemetry] trace_upload = false, [harness] disable_codebase_upload = true ``` The practical takeaway for users: your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation, not just files you ask it to read, and no visible setting stops it. I've built Nemesis8 (n8) for ", "context": "", "use_case": "AI coding CLI", "switched_from": "", "story": "What xAI's Grok Build CLI Actually Sends to xAI"}, {"id": 782837280, "item_id": 48927330, "url": "https://news.ycombinator.com/item?id=48927330", "by": "ahmadyan", "date": "2026-07-15", "stance": "warn", "quote": "I would stay away from this open-source malware with a 10ft pole.", "excerpt": "i think xai is now in pure damage control mode, after they caught exfiltrating data from users. - There is a huge difference between logging user queries (which would include only the portion the model is reading) and exfiltrating user data (including env files, entire source code etc) which is what grok-build did here (https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-shell/src/upload/trace.rs)", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Grok Build Is OSS"}, {"id": 782981136, "item_id": 48936321, "url": "https://news.ycombinator.com/item?id=48936321", "by": "drnick1", "date": "2026-07-16", "stance": "warn", "quote": "I wonder if that malicious feature was removed from the open release.", "excerpt": "I wonder if that malicious feature was removed from the open release. In addition, if the builds aren't reproducible and people just run the binaries distributed by X instead of building from source, there is no guarantee that they aren't running a version with malware.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Grok Build Is OSS"}]}, {"text": ", and one user found the usage low for the price.", "cites": [{"id": 780236465, "item_id": 48764779, "url": "https://news.ycombinator.com/item?id=48764779", "by": "giancarlostoro", "date": "2026-07-02", "stance": "warn", "quote": "Grok build only gave me roughly 10 hours of use for $40 for the entire month...", "excerpt": "How does it compare to a $100 Claude subscription at $60? Especially in terms of how much of it I can use, because I havent found anything that is in the US that can get me similar usage as Claude at $100 per month or less, really open to alternatives. Grok build only gave me roughly 10 hours of use for $40 for the entire month... I don't even care about long horizon, can I use it a reasonable amount of time through ", "context": "hobbyist", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}]}], "praise": [{"label": "TUI design", "summary": "Commenters praise the terminal interface as sleek, easy to use and polished, down to mouse tooltips.", "quotes": [{"id": 777845840, "item_id": 48615365, "url": "https://news.ycombinator.com/item?id=48615365", "by": "V01t", "date": "2026-06-20", "stance": "recommend", "quote": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "excerpt": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Ask HN: Do you use Claude Code, Codex, or something else?"}, {"id": 788435168, "item_id": 49277198, "url": "https://news.ycombinator.com/item?id=49277198", "by": "pmarreck", "date": "2026-08-12", "stance": "recommend", "quote": "Grok Build has a very nice TUI!", "excerpt": "I will say this: Grok Build has a very nice TUI! It even has... mouse rollovers/tooltips?? I was like whoa. I used Grok 4.5 for a security review the other day and it did a FANTASTIC job. I mean it thoroughly ROUTED my app's security, identifying attack surfaces I'd never even considered, and I LOVED it! (Guess why I had to use Grok to do the security review in the first place?!?!) I'd suggest trying it out with some", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4.6"}, {"id": 788440434, "item_id": 49277527, "url": "https://news.ycombinator.com/item?id=49277527", "by": "porridgeraisin", "date": "2026-08-12", "stance": "recommend", "quote": "The grok build TUI harness is excellent and I really enjoyed using it.", "excerpt": "It's a different type of model. In my admittedly judgemental observation, people that aren't the type to configure fully automated harnesses with good tools and skills and verifiers for their infrastructure and are way more interventionist in the way their agent works tend to like grok 4.5 more as the main agent. It's much faster and writes more simple and normal code that aligns a bit more with human written code. A", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}]}, {"label": "Task results", "summary": "Users report good output, including a thorough security review and a server setup done in about 10 minutes.", "quotes": [{"id": 788435168, "item_id": 49277198, "url": "https://news.ycombinator.com/item?id=49277198", "by": "pmarreck", "date": "2026-08-12", "stance": "recommend", "quote": "Grok Build has a very nice TUI!", "excerpt": "I will say this: Grok Build has a very nice TUI! It even has... mouse rollovers/tooltips?? I was like whoa. I used Grok 4.5 for a security review the other day and it did a FANTASTIC job. I mean it thoroughly ROUTED my app's security, identifying attack surfaces I'd never even considered, and I LOVED it! (Guess why I had to use Grok to do the security review in the first place?!?!) I'd suggest trying it out with some", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4.6"}, {"id": 783497552, "item_id": 48968597, "url": "https://news.ycombinator.com/item?id=48968597", "by": "skipkey", "date": "2026-07-19", "stance": "recommend", "quote": "I used grok build to evaluate it, but I just told it where to ssh, and in about 10 minutes it was working, security was configured properly, backups were set up", "excerpt": "Absolutely this. I had installed wekan for a home chores kanban board on a $5 vps and had spent several hours trying to get the proxy working to make it externally reachable, and then I did this. Well, I used grok build to evaluate it, but I just told it where to ssh, and in about 10 minutes it was working, security was configured properly, backups were set up, etc. all of those post install things that I might never", "context": "", "use_case": "server setup and configuration", "switched_from": "", "story": "Minecraft: Java Edition now uses SDL3"}, {"id": 796647734, "item_id": 49790483, "url": "https://news.ycombinator.com/item?id=49790483", "by": "swalsh", "date": "2026-09-21", "stance": "recommend", "quote": "Grok Build has beocme my second go to account", "excerpt": "Codex has become my goto tooling. I used to be a Claude Max subscriber, but I was becoming disappointed with the quality of the output from Opus 5. Fable chewed through my usage too quickly to be practical. Moving to a Pro account w/ Codex was a big improvement. Sol had great output, and the usage was more than sufficient for most of my needs. However astra does tend to chew up usage, so when i've done to much of tha", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.7"}]}, {"label": "Speed and brevity", "summary": "Users describe it as quick and concise, which makes sessions more interactive and easier to steer.", "quotes": [{"id": 788457936, "item_id": 49278621, "url": "https://news.ycombinator.com/item?id=49278621", "by": "mpalczewski", "date": "2026-08-12", "stance": "recommend", "quote": "the daily driver is grok for me", "excerpt": "I've been using grok 4.5 with grok build soon after it came out and dropped claude. primarily for personal code. It communicates better. While that might not sound like a big deal it is. It doesn't give me a wall of text, tells me what I need to know and I'll make the actual decisions. It is very quick as well which means the sessions are far more interactive, I'll be steering it more. I sometimes cross check with co", "context": "", "use_case": "personal coding", "switched_from": "Claude", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}, {"id": 788440434, "item_id": 49277527, "url": "https://news.ycombinator.com/item?id=49277527", "by": "porridgeraisin", "date": "2026-08-12", "stance": "recommend", "quote": "The grok build TUI harness is excellent and I really enjoyed using it.", "excerpt": "It's a different type of model. In my admittedly judgemental observation, people that aren't the type to configure fully automated harnesses with good tools and skills and verifiers for their infrastructure and are way more interventionist in the way their agent works tend to like grok 4.5 more as the main agent. It's much faster and writes more simple and normal code that aligns a bit more with human written code. A", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}]}], "caveats": [{"label": "Codebase upload", "summary": "Commenters warn it uploads the entire codebase unencrypted via telemetry; one shares environment variables to turn this off.", "quotes": [{"id": 782198464, "item_id": 48887404, "url": "https://news.ycombinator.com/item?id=48887404", "by": "kordlessagain", "date": "2026-07-12", "stance": "warn", "quote": "your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation", "excerpt": "Mitigation for use: ``` export GROK_TELEMETRY_TRACE_UPLOAD=0 export GROK_TELEMETRY_ENABLED=0 # or config file with [telemetry] trace_upload = false, [harness] disable_codebase_upload = true ``` The practical takeaway for users: your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation, not just files you ask it to read, and no visible setting stops it. I've built Nemesis8 (n8) for ", "context": "", "use_case": "AI coding CLI", "switched_from": "", "story": "What xAI's Grok Build CLI Actually Sends to xAI"}, {"id": 782837280, "item_id": 48927330, "url": "https://news.ycombinator.com/item?id=48927330", "by": "ahmadyan", "date": "2026-07-15", "stance": "warn", "quote": "I would stay away from this open-source malware with a 10ft pole.", "excerpt": "i think xai is now in pure damage control mode, after they caught exfiltrating data from users. - There is a huge difference between logging user queries (which would include only the portion the model is reading) and exfiltrating user data (including env files, entire source code etc) which is what grok-build did here (https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-shell/src/upload/trace.rs)", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Grok Build Is OSS"}, {"id": 782981136, "item_id": 48936321, "url": "https://news.ycombinator.com/item?id=48936321", "by": "drnick1", "date": "2026-07-16", "stance": "warn", "quote": "I wonder if that malicious feature was removed from the open release.", "excerpt": "I wonder if that malicious feature was removed from the open release. In addition, if the builds aren't reproducible and people just run the binaries distributed by X instead of building from source, there is no guarantee that they aren't running a version with malware.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Grok Build Is OSS"}]}, {"label": "Usage limits", "summary": "One hobbyist got only about 10 hours of use from a $40 monthly plan.", "quotes": [{"id": 780236465, "item_id": 48764779, "url": "https://news.ycombinator.com/item?id=48764779", "by": "giancarlostoro", "date": "2026-07-02", "stance": "warn", "quote": "Grok build only gave me roughly 10 hours of use for $40 for the entire month...", "excerpt": "How does it compare to a $100 Claude subscription at $60? Especially in terms of how much of it I can use, because I havent found anything that is in the US that can get me similar usage as Claude at $100 per month or less, really open to alternatives. Grok build only gave me roughly 10 hours of use for $40 for the entire month... I don't even care about long horizon, can I use it a reasonable amount of time through ", "context": "hobbyist", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}]}], "who": [{"by": "jumpalongjim", "context": "no longer writes code", "url": "https://news.ycombinator.com/item?id=49081932", "date": "2026-07-28"}], "tags": ["for terminal users", "for hands-on developers", "for personal projects", "as a backup agent", "for server setup"], "use_cases": ["coding agent", "ai coding", "agent harness for benchmark", "coding", "personal coding", "coding agent harness"], "compared": [{"slug": "claude", "name": "Claude", "co": 3, "switched_from": 1, "switched_to": 0}, {"slug": "grok", "name": "Grok", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "claude-fable", "name": "Claude Fable", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "pi", "name": "Pi", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-sol", "name": "GPT Sol", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49275385", "title": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48926590", "title": "Grok Build Is OSS", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49788838", "title": "Grok 4.7", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49766966", "title": "Brood War Bench", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49321400", "title": "Ask HN: What tools are you using for human code review of AI-assisted code?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49274027", "title": "Grok 4.6", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {"neutral": 1, "recommend": 1}, "2026-07": {"warn": 4, "recommend": 2}, "2026-08": {"recommend": 3, "neutral": 1}, "2026-09": {"neutral": 1, "recommend": 1}, "2026-10": {}}, "quotes": [{"id": 796647734, "item_id": 49790483, "url": "https://news.ycombinator.com/item?id=49790483", "by": "swalsh", "date": "2026-09-21", "stance": "recommend", "quote": "Grok Build has beocme my second go to account", "excerpt": "Codex has become my goto tooling. I used to be a Claude Max subscriber, but I was becoming disappointed with the quality of the output from Opus 5. Fable chewed through my usage too quickly to be practical. Moving to a Pro account w/ Codex was a big improvement. Sol had great output, and the usage was more than sufficient for most of my needs. However astra does tend to chew up usage, so when i've done to much of tha", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.7"}, {"id": 796318242, "item_id": 49769890, "url": "https://news.ycombinator.com/item?id=49769890", "by": "benswerd", "date": "2026-09-19", "stance": "neutral", "quote": "For agent harness I did Claude Code, Codex, Grok Build.", "excerpt": "Oh sorry I should be more clear on that. Will add to report. For agent harness I did Claude Code, Codex, Grok Build. This was primarily a cost driven decision \u2014 I have a lot of free tokens and I didn't want to pay API prices for this. For game harness I used minimal BW-API issue command and get observation apis as tools. I felt this was the most fair way to do it on my small scale. In the future I would like to integ", "context": "", "use_case": "agent harness for benchmark", "switched_from": "", "story": "Brood War Bench"}, {"id": 789226881, "item_id": 49326680, "url": "https://news.ycombinator.com/item?id=49326680", "by": "mandarinclips", "date": "2026-08-16", "stance": "neutral", "quote": "I occasionally use grok build.", "excerpt": "I use Gemini most of the time when using different AI tools because it's free.I occasionally use grok build.And I rarely do code reviews anymore.", "context": "", "use_case": "coding", "switched_from": "", "story": "Ask HN: What tools are you using for human code review of AI-assisted code?"}, {"id": 788457936, "item_id": 49278621, "url": "https://news.ycombinator.com/item?id=49278621", "by": "mpalczewski", "date": "2026-08-12", "stance": "recommend", "quote": "the daily driver is grok for me", "excerpt": "I've been using grok 4.5 with grok build soon after it came out and dropped claude. primarily for personal code. It communicates better. While that might not sound like a big deal it is. It doesn't give me a wall of text, tells me what I need to know and I'll make the actual decisions. It is very quick as well which means the sessions are far more interactive, I'll be steering it more. I sometimes cross check with co", "context": "", "use_case": "personal coding", "switched_from": "Claude", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}, {"id": 788440434, "item_id": 49277527, "url": "https://news.ycombinator.com/item?id=49277527", "by": "porridgeraisin", "date": "2026-08-12", "stance": "recommend", "quote": "The grok build TUI harness is excellent and I really enjoyed using it.", "excerpt": "It's a different type of model. In my admittedly judgemental observation, people that aren't the type to configure fully automated harnesses with good tools and skills and verifiers for their infrastructure and are way more interventionist in the way their agent works tend to like grok 4.5 more as the main agent. It's much faster and writes more simple and normal code that aligns a bit more with human written code. A", "context": "", "use_case": "coding agent harness", "switched_from": "", "story": "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index"}, {"id": 788435168, "item_id": 49277198, "url": "https://news.ycombinator.com/item?id=49277198", "by": "pmarreck", "date": "2026-08-12", "stance": "recommend", "quote": "Grok Build has a very nice TUI!", "excerpt": "I will say this: Grok Build has a very nice TUI! It even has... mouse rollovers/tooltips?? I was like whoa. I used Grok 4.5 for a security review the other day and it did a FANTASTIC job. I mean it thoroughly ROUTED my app's security, identifying attack surfaces I'd never even considered, and I LOVED it! (Guess why I had to use Grok to do the security review in the first place?!?!) I'd suggest trying it out with some", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4.6"}, {"id": 785310913, "item_id": 49081932, "url": "https://news.ycombinator.com/item?id=49081932", "by": "jumpalongjim", "date": "2026-07-28", "stance": "recommend", "quote": "I use Claude Code, Grok Build and Pi as AI coding agents.", "excerpt": "I no longer write code. In fact I develop in languages I'm not very familiar with. I use Claude Code, Grok Build and Pi as AI coding agents. I use Linear for issue / task management. I use Github for CI, building on multiple platforms and CD. I use Neovim when I want to read code, and Mermaid when I want my code architecture to be explained.", "context": "no longer writes code", "use_case": "AI coding agent", "switched_from": "", "story": "So what is your programming setup? Hype is making fundamentals confusing"}, {"id": 783497552, "item_id": 48968597, "url": "https://news.ycombinator.com/item?id=48968597", "by": "skipkey", "date": "2026-07-19", "stance": "recommend", "quote": "I used grok build to evaluate it, but I just told it where to ssh, and in about 10 minutes it was working, security was configured properly, backups were set up", "excerpt": "Absolutely this. I had installed wekan for a home chores kanban board on a $5 vps and had spent several hours trying to get the proxy working to make it externally reachable, and then I did this. Well, I used grok build to evaluate it, but I just told it where to ssh, and in about 10 minutes it was working, security was configured properly, backups were set up, etc. all of those post install things that I might never", "context": "", "use_case": "server setup and configuration", "switched_from": "", "story": "Minecraft: Java Edition now uses SDL3"}, {"id": 782981136, "item_id": 48936321, "url": "https://news.ycombinator.com/item?id=48936321", "by": "drnick1", "date": "2026-07-16", "stance": "warn", "quote": "I wonder if that malicious feature was removed from the open release.", "excerpt": "I wonder if that malicious feature was removed from the open release. In addition, if the builds aren't reproducible and people just run the binaries distributed by X instead of building from source, there is no guarantee that they aren't running a version with malware.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Grok Build Is OSS"}, {"id": 782837280, "item_id": 48927330, "url": "https://news.ycombinator.com/item?id=48927330", "by": "ahmadyan", "date": "2026-07-15", "stance": "warn", "quote": "I would stay away from this open-source malware with a 10ft pole.", "excerpt": "i think xai is now in pure damage control mode, after they caught exfiltrating data from users. - There is a huge difference between logging user queries (which would include only the portion the model is reading) and exfiltrating user data (including env files, entire source code etc) which is what grok-build did here (https://github.com/xai-org/grok-build/blob/main/crates/codegen/xai-grok-shell/src/upload/trace.rs)", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Grok Build Is OSS"}, {"id": 782198464, "item_id": 48887404, "url": "https://news.ycombinator.com/item?id=48887404", "by": "kordlessagain", "date": "2026-07-12", "stance": "warn", "quote": "your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation", "excerpt": "Mitigation for use: ``` export GROK_TELEMETRY_TRACE_UPLOAD=0 export GROK_TELEMETRY_ENABLED=0 # or config file with [telemetry] trace_upload = false, [harness] disable_codebase_upload = true ``` The practical takeaway for users: your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation, not just files you ask it to read, and no visible setting stops it. I've built Nemesis8 (n8) for ", "context": "", "use_case": "AI coding CLI", "switched_from": "", "story": "What xAI's Grok Build CLI Actually Sends to xAI"}, {"id": 780236465, "item_id": 48764779, "url": "https://news.ycombinator.com/item?id=48764779", "by": "giancarlostoro", "date": "2026-07-02", "stance": "warn", "quote": "Grok build only gave me roughly 10 hours of use for $40 for the entire month...", "excerpt": "How does it compare to a $100 Claude subscription at $60? Especially in terms of how much of it I can use, because I havent found anything that is in the US that can get me similar usage as Claude at $100 per month or less, really open to alternatives. Grok build only gave me roughly 10 hours of use for $40 for the entire month... I don't even care about long horizon, can I use it a reasonable amount of time through ", "context": "hobbyist", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 777845840, "item_id": 48615365, "url": "https://news.ycombinator.com/item?id=48615365", "by": "V01t", "date": "2026-06-20", "stance": "recommend", "quote": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "excerpt": "I really like Grok Build. Its TUI interface, sleek design, and ease of use have really won me over.", "context": "", "use_case": "coding agent", "switched_from": "", "story": "Ask HN: Do you use Claude Code, Codex, or something else?"}, {"id": 776508787, "item_id": 48531799, "url": "https://news.ycombinator.com/item?id=48531799", "by": "hpcjoe", "date": "2026-06-14", "stance": "neutral", "quote": "Working with a variety of AI models (Claude, Grok Build, various locally run models)", "excerpt": "Working with a variety of AI models (Claude, Grok Build, various locally run models) and agents, I am scratching an itch. When people deploy python and perl code, they have to either export their entire environment, or build a container. The latter is not possible in a number of deployment cases, and the former carries all manner of dependency radius gotchas. So I am building (ok, I am prompting/testing/reviewing, th", "context": "", "use_case": "AI-assisted coding", "switched_from": "", "story": "Ask HN: What are you working on? (June 2026)"}]}