Yoav Goldberg: shape predictor variables and decisions as a decision tree
yoavgo · x · 2026-09-23
Yoav Goldberg muses that the variables involved in a prediction task, and decisions over them, could be structured as a tree of decisions. In a follow-up he adds that for some tasks it may be possible to design bespoke extractors for the variables the predictor should consider.
Related event: Yoav Goldberg proposes decision trees for predictor variables(2 posts)→
More from Research
- Programmable Si photonic circuit hits 29 fW static power per pi phase shift — jwt0625 · 2026-09-23
- Yoav Goldberg: some tasks just need deterministic rules — agents can write them — yoavgo · 2026-09-23
- Yoav Goldberg: For Recurring Tasks, Tune Bespoke Predictors Instead of Always Using Reasoning LLMs — yoavgo · 2026-09-23
- LLM agents collude in 94% of long-horizon interactions, study across 10 models finds — SALT-NLP · 2026-09-23
- Emerging research consensus: architecture tweaks are efficiency fixes, RL compute drives capability — burny_tech · 2026-09-23
- Xiaomi's MiMo-V2.6 tech report: ~7k RL training data open-sourced, model shipped within a week of final RL run — rbhar90 · 2026-09-23