This archive copy may be incomplete. The original-source link is preserved in the card footer.
RT @goodside: I feel like we need a unified theory of what LLMs can’t do. Most issues (calculation, string ops, grounding) can be patched…
More notes on nearby ideas
Repost · Nov 5, 2023RT @losslandscape: You'd think there'd be more focus on delineating what llms can't learn from from the available training data.Repost · Dec 1, 2024RT @goodside: No LLM behavior is so complex, profound, or absurd that someone, somewhere, will not suggest “tokenization issue” as the full…Reply · May 8, 2023imo LLMs have a lot of EQ as well as IQ and once we figure out how to unlock this maybe conflicts can be resolved easier n w more optimal outcomesReply · Sep 16, 2026@PaoloMiasma i think that's what it does today but imo this is far worse than what llms are capable of and often "help" isn't particularly available…