Taste-Bench shows AI agents make poor long-term strategic choices, top model under 60%
The Decoder · rss · 2026-10-18
The Decoder covers Taste-Bench, a new benchmark testing how well AI agents make strategic choices during long-running tasks.
- Even the best model, GPT-5.6 Sol, picks the right path on just under 60% of simple binary questions.
- Thinking longer doesn't help, suggesting long-horizon strategic judgment is a widespread weakness of current models.
More from Research
- Attention head acts as a switch: mechanistic interp case flips model answer from No to Yes — CatAstro_Piyush · 2026-10-18
- Harvard's open-source ML Systems textbook hits 29.1K stars on GitHub — mdancho84 · 2026-10-18
- 25-author working paper examines feasibility of a hardwired pause on frontier AI training — wfithian · 2026-10-18
- AI meets archaeology: data science helps reveal past epidemics — ArtificialOther · 2026-10-18
- Weight decay scaling was in the original AdamW paper — first author Loshchilov is on X — SeunghyunSEO7 · 2026-10-18
- Pedro Domingos reminds: every model learned by gradient descent is approximately a kernel machine — pmddomingos · 2026-10-18