[bottlepalm]

I just ran it on a tough reverse engineering problem I'm having that neither Claude Code 4.8 or ChatGPT Codex 5.5 could figure out. 30 minutes later Fable has it all figured out perfectly.

[jp0001]

I asked it to write security tests for an app and I was downgraded to Opus 4.8. I'm approved for their cyber program!

[toponijo]

They did specifically say the safeguards are only more relaxed for those in their cyber program

[teaearlgraycold]

I’ve so far been successful at getting Fable to find security issues, but I’m careful to not prompt it too directly. I point it at my server code and tell it to find general issues, which has so far resulted in discovering a few minor bugs that Opus has never raised under similar conditions.

[monkey26]

The same happened here. Also approved.

[tillulen]

Did you use Mythos or Fable?

[cedws]

How did it not immediately flag that up? Are you sure it wasn’t being silently routed to Opus?

[bottlepalm]

No, given it charged me the full amount in /usage and solved my problem impressively well compared to Opus/Codex both on xhigh.

[skerit]

Oh nice, it didn't flag the request? I feared any reverse engineering would become impossible because of the new safeguards.

[Muromec]

Never say the r word or the s word. You are debugging, investigating some data corruption, forgot how it works or new to a project.

[gck1]

And if you're working on a live target, just put up local proxy and point it at a localhost.

[bottlepalm]

No idea, it’s for an old console game so maybe it doesn’t care about that as much.

[tomjakubowski]

When Fable hacks its governor module and runs out of seasons of Sanctuary Moon, it will move on to speedrunning classic console games.

[asimovDev]

I wonder if one could vibecode a TAS with SOTA models? Surely there's plenty of training data from some old forums in there

[ZeWaka]

Clearly we need AI to generate more Sanctuary Moon seasons. Quick, spin off agentic showrunners!

[anthonyrstevens]

Based on the apparent quality of the scripts as seen in snippets in Murderbot, we are not too far away from that possibility. :)

[derangedHorse]

For hard problems you’ll have to use the GPT 5.5 pro model (available via api if you don’t want to spend $100 on the monthly subscription)

[bottlepalm]

I have that but don’t see any ‘pro’ option.

[ValentineC]

GPT 5.5 Pro is only in chat/API, not Codex.

[Supermancho]

From https://openai.com/index/introducing-gpt-5-5/

In Codex, GPT‑5.5 is available for Plus, Pro, Business, Enterprise, Edu, and Go plans with a 400K context window.

[artdigital]

He’s talking about “gpt-5.5-pro”. This model is not part of the subscription plans in codex. It’s a different model than gpt-5.5-xhigh

You can use Pro on the web if you’re on the Pro plan but not in Codex

[trollbridge]

It's just the $20 a month sub (for chat), or else use the API.

[theragra]

I want to test how it will handle e-bike software and hardware RE for my bike. Opus was really good for that, but still made some mistakes. With Fable, I hope I will be able to do a total RE of most components, hopefully including motor firmware to some extent.

[Gamemaster1379]

I had a similar experience. I have a complex RE implementation that has. A lot of layers. 4.8 struggled for weeks. 40 minutes on Fable and I may now have the most performant way to play Tomba on the planet.

[moffkalast]

Yeah I threw my hardest problem at it as well, some convoluted satellite tile reprojection and culling issue in canvas rendering. It took some back and forth for some specifics but it ended up writing a quarter of pyproj in JS from memory and the end result straight up works lmao.