{"slug": "jeff", "name": "Jeff", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 2, "commenters": 2, "warners": 0, "score": 1.959, "rising": 2.0, "first": "2026-09-28", "latest": "2026-09-29", "why": "to show it's possible to build an MVP on open weights without years of work and millions of dollars.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 2, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0], "listed": false, "loved": [], "caveat": "", "short_quote": "to show it's possible to build an MVP on open weights without years of work and millions of dollars.", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["Jeff"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 798260336, "item_id": 49891271, "url": "https://news.ycombinator.com/item?id=49891271", "by": "ioma8", "date": "2026-09-29", "stance": "recommend", "quote": "Works like a charm", "excerpt": "I made super quick file sorter with it.. Works like a charm: https://github.com/ioma8/jeff-sort", "context": "", "use_case": "file sorting", "switched_from": "", "story": "Jeff \u2013 Jev-compatible 0.8B decision models, trained at home, ~30 ms"}, {"id": 798161712, "item_id": 49885107, "url": "https://news.ycombinator.com/item?id=49885107", "by": "tbeseda", "date": "2026-09-28", "stance": "recommend", "quote": "to show it's possible to build an MVP on open weights without years of work and millions of dollars.", "excerpt": "For _your_ classification it's unacceptable. The OP seems to have anticipated this and mentions you can fine tune it for your use case. Did you try that? I don't think the point is to displace Jev, but to show it's possible to build an MVP on open weights without years of work and millions of dollars. Why (presumably) an engineer would dismiss exploring a lightweight, custom alternative to locking into a fashionable ", "context": "", "use_case": "custom lightweight decision model", "switched_from": "", "story": "Jeff \u2013 Jev-compatible 0.8B decision models, trained at home, ~30 ms"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["file sorting", "custom lightweight decision model"], "compared": [{"slug": "jev", "name": "Jev", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 798141520, "item_id": 49883845, "url": "https://news.ycombinator.com/item?id=49883845", "by": "firelex", "date": "2026-09-28", "stance": "recommend", "quote": "Jeff is a set of small, open-weight Qwen3.5 and Gemma fine-tunes for zero-shot classification", "excerpt": "Hi HN. Jeff is a set of small, open-weight Qwen3.5 and Gemma fine-tunes for zero-shot classification, with respectable out-of-the-box performance, meant to be slotted right into code (or fine-tuned further as needed). You give them a situation and a list of options; they return a calibrated probability for each, in one forward pass, with no text generation. The 2B scores 83.1% on a five-benchmark panel (Jev's publish", "context": "built it, not affiliated with TypeSafe", "use_case": "fast local decision models", "switched_from": "", "story": "Jeff \u2013 Jev-compatible 0.8B decision models, trained at home, ~30 ms"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49883844", "title": "Jeff \u2013 Jev-compatible 0.8B decision models, trained at home, ~30 ms", "mentions": 3}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {"recommend": 2}, "2026-10": {}}, "quotes": [{"id": 798260336, "item_id": 49891271, "url": "https://news.ycombinator.com/item?id=49891271", "by": "ioma8", "date": "2026-09-29", "stance": "recommend", "quote": "Works like a charm", "excerpt": "I made super quick file sorter with it.. Works like a charm: https://github.com/ioma8/jeff-sort", "context": "", "use_case": "file sorting", "switched_from": "", "story": "Jeff \u2013 Jev-compatible 0.8B decision models, trained at home, ~30 ms"}, {"id": 798161712, "item_id": 49885107, "url": "https://news.ycombinator.com/item?id=49885107", "by": "tbeseda", "date": "2026-09-28", "stance": "recommend", "quote": "to show it's possible to build an MVP on open weights without years of work and millions of dollars.", "excerpt": "For _your_ classification it's unacceptable. The OP seems to have anticipated this and mentions you can fine tune it for your use case. Did you try that? I don't think the point is to displace Jev, but to show it's possible to build an MVP on open weights without years of work and millions of dollars. Why (presumably) an engineer would dismiss exploring a lightweight, custom alternative to locking into a fashionable ", "context": "", "use_case": "custom lightweight decision model", "switched_from": "", "story": "Jeff \u2013 Jev-compatible 0.8B decision models, trained at home, ~30 ms"}]}