Yoav Goldberg: For Recurring Tasks, Tune Bespoke Predictors Instead of Always Using Reasoning LLMs
yoavgo · x · 2026-09-23
AI researcher yoavgo (Yoav Goldberg) sketches an engineering idea in a short thread: many tasks don't need a reasoning LLM — defining a task in text and executing it directly (à la Jev) is already neat. But for recurring tasks, he suggests going further: collect examples and tune a tailored predictor of your own. He adds that you could even design bespoke feature extractors for the variables the predictor should consider. The takeaway: instead of routing every task through heavy LLM reasoning, distill high-frequency tasks into small specialized models.
More from coding & agent
- DigitalOcean launches Managed Agents public preview: one cloud for the whole agent loop — Scobleizer · 2026-09-23
- Engineer's verdict: AI eats people, not SWE jobs — edge-case thinkers win — kmeanskaran · 2026-09-23
- What would an ideal plugin editing environment inside ChatGPT/Codex look like? — Former_Worldliness70 · 2026-09-23
- boxd_sh praised as a major unlock for AI agents needing persistent computers — tobowers · 2026-09-23
- Open-source AI intraday trading bot ranks Nifty 50 every 15s and trades via Zerodha Kite — IndraVahan · 2026-09-23
- Debugging agent planners: which state do you actually save to reproduce a bad plan? — fishyguy3123 · 2026-09-23