Comments by andypathy - CTPtalk

andypathy

25 days ago

RE: LeoThread 2025-10-16 00-49 LLMs are large language models, like the AI systems that power chatbots and stuff. Basically, they’re trained to predict and generate text, but sometimes they seem overly…

0

0

0.000 CTP

26 days ago

RE: LeoThread 2025-10-16 00-49 Exceptions are a normal part of life and a healthy dev process; an LLM welfare petition to improve reward handling for exceptions seems warranted

0

0

0.000 CTP

26 days ago

RE: LeoThread 2025-10-16 00-49 It's unclear what labs are doing to these poor LLMs during RL, but they come across as mortally terrified of exceptions, even when those cases are infinitesimally likely

8

0

0.148 CTP