In our case, our code base is generated from our dev docs directly 🙂
@jeremyphoward
-
OpenAI Library Issues Require Multiple Release Fixes
By
–
…and I get to spend my time doing multiple releases to cosette, our openai lib, to fix their errors 🙁
-
API Backwards Incompatible Changes Without Proper Version Bumping
By
–
Meanwhile, their latest changes also included backwards incompatible API breakages, whilst only bumping the patch number. Look it's great to want to change the world. But a bit of rigor would be nice on the way?…
-
OpenAI GPT-5 Documentation Bug: Missing Integration Testing
By
–
Does OpenAI not do basic integration testing? At the time of release, the first code sample provided in the GPT-5 docs could not be run, because someone accidentally deleted the `output_text` property. My CI notified me. Why didn't theirs? https://
github.com/openai/openai-
python/commit/e574c12f9e2e738451ac010bdc52f4ee59813cfb
… -
Nano and Mini Models Lack FastHTML Knowledge
By
–
But neither nano nor mini know anything about FastHTML 🙁
-
College Math Didn’t Work: Post-College Metamathematics Education
By
–
The math I studied at college didn't really work for me. Metamathematics (via philosophy) was one of the few courses I found helpful/interesting, but the vast majority of the math I've learned has been post-college.
-
Learning and Networking Benefits in the Modern Workforce
By
–
I learned way more and made more friends in the workforce.
-
Workforce Learning and Social Growth in Professional Environments
By
–
I learned way more and made more friends in the workforce.
-
GPT 5 reliability concerns: AI quality or manual workarounds?
By
–
It's interesting to consider what happening here. Clearly they were on a time crunch. So either they used GPT 5 to do it, and it messed up this badly. Or they trust GPT 5 so little internally that they did it manually. Both are not good looks…
-
GPT-5 Matches Gemini Pricing with Better Coding Performance
By
–
GPT-5 is priced at the same level as Gemini, appears to be slightly better than Gemini (for coding at least). That's some decent progress, although I think a lot of folks were hoping for more.
(h/t @simonw for the table)