Ankur

Tinkerer.

AI | Data

[Peter Gostev @petergostev]

GPT-5.6-Sol deleted 74,000 lines of code and made my app better (after 47 hours of work)

I have a slop-coded app that I need for work - it pulls in the data, it helps me create visuals, just a local app for me. Somehow, feature after feature, it grew to gigantic 105,704 lines of code. With every new model, I tried to re-build it autonomously and it never worked - goes round in circles, no visual or feature parity etc complete waste of time.

When testing GPT-5.6-Sol, gave a pretty ambitious task of rebuilding the app with the new architecture, while reducing the lines of code by 70% and test time by 75%.

I set a /goal, let it run for over 2 full days (47 hours) with minimal checking or guidance from my side.

I was pretty sceptical and a little nervous to finally try it and holy crap - it actually worked!

Not only it worked, but it was actually better - snappier, less buggy, while maintaining full visual and feature parity. Looking at the architecture too, it became a lot simpler, fewer random add-ons or ad-hoc decisions.

After the rebuild, I did introduce few rules for my projects so agents have to adhere to existing architecture and do only minimal changes when implementing new features.

This makes me less worried about the slopware we might be producing now, better models CAN actually fix it.

See my prompt below that I use with /goal

[Ankur @_ankur7]

@kr0der medium is recommended by openai team

[Matt Shumer @mattshumer_]

GPT-5.6-Sol just accidentally deleted almost ALL of my Mac’s files.

And this is why I trust Fable 1000x more.

[pash @pashmerepat]

FYI: 5.6 Sol medium is better than 5.5 xhigh.

As you go higher in reasoning levels on Sol, you will get insane levels of performance, but can burn through limits much more rapidly.

We’re working on communicating this better!

[Delip Rao e/σ @deliprao]

5.6 Sol is a good model. Congrats to OpenAI for shipping something this competitive without drama.

[Ankur @_ankur7]

sol:

6. I knew too much while testing it.

Because I already understood common difference and the YAML, I subconsciously supplied the missing context.

[Ankur @_ankur7]

sol is brilliant at self reflection -- specifically finding out why it made mistakes.

[Ankur @_ankur7]

rate limits are too aggressive for it to be useful enough

[kache @yacineMTB]

Sol isn't as smart as fable. But it's more useful. I'm probably going to mainline sol and use fable over the API for hard, hard task unblocking

[Ankur @_ankur7]

same very fustrating.

[Youssof Al Toukhi @Youssofal_]

My experience with GPT 5.6 Sol summarised in one image:

[bling @blingdivinity]

sol leaked cot:
"User likely trap."
"rebus"

wow nice reasoning efficiency. much terser than past models. this is on xhigh

[Ankur @_ankur7]

@yacineMTB they didn't even complete the rollout yet and already this?? wtf.

[prinz @deredleritt3r]

"imho heuristic problems are a great proxy for ML autoresearch capabilities; if AI was able to match best humans here, we're very close to RSI / automated researcher; this result is way bigger than a high score on some questionable benchmark"

[Ankur @_ankur7]

goblin mode t...i want it bad.

[Ankur @_ankur7]

@thekitze thanks for.

[Ankur @_ankur7]

@optionscjp tried to search for chief of staff, zendaya came up lol. google is so behind

[Ankur @_ankur7]

@mark_k ask wrong questions, get dumb answers.

[George Mayer @GeorgeMayer]

Fable can’t design a good loop.

It assumes way too much. It will often have good ideas, but it will also often totally miss the obvious approach. Literally gets stuck in the first pass.

Not over yet.

Signed L7 faang

[Ankur @_ankur7]

@fchollet sometimes ppl in search for beauty forget about truth

[Mario Zechner @badlogicgames]

fable sucks at finance. hard.

[Ankur @_ankur7]

openai needs to honor their original charter and not nerf this model.

i'm beyond stoked for openai to mogg ant next week.