Ai2 Asks Whether Prompting or Training Can Make LLMs Give More Useful Advice
allen_ai · x · 2026-11-14
Ai2 explains the motivation behind XYBench: testing whether prompting or training changes can lead to more useful advice from LLMs, hoping to help researchers build assistants that guide users toward helpful solutions even when they don't know the right questions to ask.
This thread-closer accompanies the XYBench release; the key finding remains that all five evaluated models steered users away from mistaken approaches less often than human reference answers, even when goals were spelled out.
More from Research
- NYU Courant launches Center for Mathematics and AI, co-directed by Bruna and Vicol — kchonyc · 2026-11-14
- mariofilho: Pareto plots should be mandatory for benchmarks — mariofilhoml · 2026-11-14
- MIT's AI 'mechanic' can read and edit the internals of other neural networks, Nature reports — marinkazitnik · 2026-11-14
- Rewiring just 47 neurons induces emergent misalignment in Qwen, then makes it interpretable — maxsloef · 2026-11-14
- Antithesis spent 8 years cracking NetHack Ascension, now clears ~80% of seeds in under 5 minutes — spikedoanz · 2026-11-14
- 5.46M-param touch model LingBot-Touch pokes straws through sealed lids autonomously — Puzzleheaded-Buy3008 · 2026-11-14