a prompt I've been using a lot recently:
implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know
Ahhhh, Codex 5.3 (xhigh) with a vague prompt just solved a bug that I and others have been struggling to fix for over 6 months. Other reasoning levels with Codex failed, Opus 4.6 failed. Cost $4.14 and 45 minutes. Full trace plus includes original issue: https://t.co/DbBACN2HLj
I know this prompt is relatively bad. Honestly, our stable release is in a week, and I was throwing some Hail Marys at the frontier models to see if I could get a clean, understandable fix for some of these bugs. By using `gh`, it grabs much better context from the issue, so its not terrible.
The best thing that Codex did was eventually start reading GTK4 source code. That's where I ended up (see my GH issue), and I knew the answer was somewhere in there, but I didn't have the time or motivation to do it myself. The other models never went there, and lower reasoning efforts with 5.3 didn't go there either. Only xhigh went there. I think that was a critical difference.
The final fix was decent. It was small, all in a single file, and very understandable. It had one bug I identified (you can see in the trace), and then I manually cleaned up some style. But, it did a great job.
Definitely an "it's so over" moment. But at the same time, it feels amazing because now our next stable release will have this fix and I was able to spend the time working on other fixes as it went.
I needed ideas for board games my daughter would like
- Deep Research in ChatGPT based on age, preferences, what board games she likes. asked for a list of 10
- Copy pasted results into Nano Banana Pro to create infographic with rules
I got Zingo and The Sneaky squirrel game
We challenged Antigravity to solve the Inverted Pendulum on a custom mechanical system it had never seen before.
Antigravity analyzed hardware specs, coded the control algorithm, and fine-tuned parameters based on performance plots.
See it in action. 👇
👑 Think YOU’D rule wisely?
Every case you solve builds your unique King/Queen profile. Be just. Be ruthless. Be legendary. ➜ https://t.co/UODHCAwO2P
#gaming#AI#AIgame#KingMaker
If you live in Germany do not fall for the trap of the 1000/50 mbit @vodafone_de Kabel Internet. @deutschetelekom Telekom VDSL (50/10) is faster, better customer service and you get what you pay for.
@pianomarvel I missed all the promo codes for xmas because they were never publicized in the app / website but only here :(. Is there any code still working for 1y sub?