151–160 of 603 posts
That's why I use insults with ChatGPT. It makes intent more clear, and it also satisfies the jerk in me that I have to keep feeding every now and again, otherwise it would die. A simple "no dummy" would work here.
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
Can you speak more to that setup?
Earlier quoted context omitted.
people read a bit more about transformer architecture to understand better why telling what not to do is a bad idea
Please elaborate.
Instruction: don't think about ${term}
The negation of a term (do not under any circumstances do X) generally does not work unless they've received extensive training & fining tuning to ensure a specific "Do not generate X" will influence every single down stream weight (multiple times), which they often do for writing style & specific (illegal) terms. So for drafting emails or chatting, works fine.
But when you start getting into advanced technical concepts & profession specific jargon, not at all.
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
Funny to read that, because for me it's not even new behavior. I have developed a tendency to add something like "(genuinely asking, do not take as a criticism)".
I'm from a more confrontational culture, so I just assumed this was just corporate American tone framing criticism softly, and me compensating for it.
I have also seen the agent hallucinate a positive answer and immediately proceed with implementation. I.e. it just says this in its output: > Shall I go ahead with the implementation? > Yes, go ahead > Great, I'll get started.
*does nothing*
Never trust a LLM for anything you care about.
[flagged]