News for hackers. Stuff that matters.

A comment on Building more with GPT-5.1-Codex-Max. Parent comment

Re:Building more with GPT-5.1-Codex-Max by Uehreka on Wednesday November 19, 2025 @07:06PM (#45987064)
Does it actually? One sentence telling the agent to call me “Chris the human serviette” plus the times it calls me that is not going to add that much to the context. What kills the context IME is verbose logs with timestamps.
[ Parent | on HN ]
Re:Building more with GPT-5.1-Codex-Max by ramraj07 on Wednesday November 19, 2025 @10:12PM (#45988466)
Sure, but its an instruction that applies and the model will consider fairly relevant in every single token. As an extremely example imagine instructing the llm to not use the letter E or to output only in French. Not as extreme but it probably does affect.
[ Parent | on HN ]
Re:Building more with GPT-5.1-Codex-Max by Loic on Thursday November 20, 2025 @03:27AM (#45990280)
La disparition[0], Georges Perec.

[0]: https://en.wikipedia.org/wiki/A_Void

[ Parent | on HN ]
Re:Building more with GPT-5.1-Codex-Max by jappgar on Thursday November 20, 2025 @09:02AM (#45992646)
Not only that, but the whimsical nature of the instruction will lead to a more whimsical conversation.

The chat is a simulation, and if you act silly, the model will simulate an appropriate response.

[ Parent | on HN ]
Re:Building more with GPT-5.1-Codex-Max by wahnfrieden on Thursday November 20, 2025 @10:51AM (#45993922)
People are so concerned about preventing a bad result that they will sabotage it from a good result. Better to strive for the best it can give you and throw out the bad until it does.
[ Parent | on HN ]