Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

What are your custom instructions. When I drop your first message into 'my' ChatGPT 5.1, the first paragraph returned is:

"Short answer: yes, the idea and overall feature are solid and “cool” for a platform – environment-aware static bundling + filtering + preloading is a real capability, not fluff. The implementation is workable but has a few concrete problems and some messy spots. (...)"



I tried it again with instructions throughout, to be brutally honest and objective: https://chatgpt.com/share/691b4035-0ed8-800a-bee3-ae68e2a63c...

It still did this. Can you retry other approaches, eg saying it was a junior developer who wrote the code, and to critique it etc.

Is it sycophantic regardless? Or is it objective? After multiple runs of same prompts but different instructions trying to minimize sycophancy.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: