Dev: Jev could run cheaply in browsers — classification tasks were shoehorned into LLMs
GabGarrett · x · 2026-09-18
The author argues Jev is obviously a big deal: it's cheap enough to run in a customer's browser. Many classification tasks were shoehorned into LLMs, which are good at them but not efficient for that purpose — Jev fills that gap. He praises the typesafeai team.
Related event: Jev's Viral Success Exposes AI Developers' Knowledge Gaps(4 posts)→
More from Models
- Epoch AI audits 15 AI benchmarks: only 4 safe to trust at face value — Jsevillamol · 2026-09-18
- Report: Hackers Used a Loosened-Guardrail Opus 5 to Breach OpenAI's Internal Monorepo — teortaxesTex · 2026-09-18
- Fine-tuned 4B model as a decision scorer with temperature-scaled confidence — Gradio · 2026-09-18
- Inside Astra's ASCII art: coordinate painting with character textures, not SVG conversion — dyot_meet_mat · 2026-09-18
- Researcher Apologizes for Misleading Leaderboard Submission, Promises Rule-Compliant Rerun — AlbertQJiang · 2026-09-18
- Noam Brown's Dwarkesh podcast: a capabilities researcher 'freaking everyone out' on safety — Apprehensive_Sand951 · 2026-09-18