Re:LLMs are mortally terrified of exceptions
by comex on Friday October 10, 2025 @02:28AM
(#45535889)
Reinforcement learning by definition operates on reward functions.
Re:LLMs are mortally terrified of exceptions
by LeifCarrotson on Friday October 10, 2025 @09:46AM
(#45538995)
LLMs do use simple "word prediction" in the pretraining step, just ingesting huge quantities of existing data. But that's not what LLM companies are shipping to end users.
Subsequently, ChatGPT/Claude/Gemini/etc will go through additional training with supervised fine-tuning, reinforcement learning with reward functions whether human-supervised feedback (RLHF) or reward functions (RLVR, 'verified rewards').
Whether that fine-tuning and reward function generation give them real "intelligence" is open to interpretation, but it's not 100% plagarism.
Re:LLMs are mortally terrified of exceptions
by aoeusnth1 on Friday October 10, 2025 @03:37PM
(#45542882)
You used the word reinforcing, and then asserted there's no reward function. Can you explain how it's possible to perform RL without a reward function, and how the LLM training process maps to that?
Re:LLMs are mortally terrified of exceptions
by MakeAJiraTicket on Friday October 10, 2025 @07:38PM
(#45545028)
LLM actions are divorced from that reward function, it's not something they consult or consider. Reward function in that context doesn't make sense.
These aren't operating on reward functions because there's no internal model to reward. It's word prediction, there's no intelligence.