Aze Gallo

@thsottiaux Ugh, I was so close to finally being able to use one of my banked resets 😂

10M! New day, new usage reset for paid users of Codex and ChatGPT Work. Lands in the next hour. Enjoy.

@TheBradOwen @wacamasta Your comment section is a weird place 😳

@wacamasta Uh, because I drink water in between alcohol while on vacation

I guess there’s some new trend about having a friend hand-feed your wife food. They got me good…

@RedDragonPokerz @LodgePokerClub Not talking about Lucid is grounds for termination

@omarsar0 This method feels like it would lead to more compute issues. I have never actively tried to maximize my usage before. If I knew fable was (even 50%) permanently on the sub I’d go back to normal usage

I don't think Anthropic realizes how disruptive these changes are to users. I appreciate the extension, but please stop playing games. Either keep it under the subscriptions or put it under the API already.

@notismaelvega @madarco @mattshumer_ @jxnlco I guess you just have to weigh the risk of getting your machine nuked vs having to say "no this is fine" once in a while, or doing proper sandboxing 🤷‍♂️

@madarco @mattshumer_ @azegallo @jxnlco it's quite conservative. sometimes, the classifier blocks some useful commands arguing that it doesnt go with the main task. and afaik, it burns tokens faster

GPT-5.6-Sol just accidentally deleted almost ALL of my Mac’s files. And this is why I trust Fable 1000x more.

@shadcn Have you heard of @neovim?

I still need a really good code editor. Are we going too fast in the other direction?

@mattshumer_ @jxnlco Models are stupid. They completely lack intelligence. Auto review has saved me from dozens of actions that would have sucked. And even then bad things have still happened (GPT and Claude). Autoreview at minimum. Sandbox/external machine preferable.

@azegallo @jxnlco Because models aren't stupid, and the odds something like this happens is probably lower than w/ a human dev

@mattshumer_ @jxnlco Curious why you wouldn't be using at least auto review on a valuable system?

@jxnlco Full access -- I have done many hundreds of sessions with zero issues in the past, even on very weak models

@thdxr @SlackHQ Please please please

someone at @SlackHQ please add a reply feature. i'm begging you just copy discord DO NOT GET CREATIVE please

@GazzyB1233 Gg

1500bb. UTG raises 3k. CO calls. I rip 32k with 99, and CO calls with QQ and covering…

@RhysSullivan @anomalyco @thdxr Copying Reeboks logo

did @anomalyco swap from copying Anthropics logo to copying SpaceXAI's logo?

@mitchellh better perf tends to have this magical cascading effect. always chase it.

Mind boggling to me that I can make a thing faster and there's always people that ask "but why?" What kind of mentality is that? The pursuit of excellence does not need justification. Also, I find in so many cases, we can't know the impact of an improvement until we do it. For example, one I've talked about before: Ghostty's high IO throughput has enabled terminal program (emulator and TUI) fuzzing at a speed thats incomparably fast to prior solutions. This has resulted in upstream patches to resolve issues in popular projects like btop, tmux, and more. Speed enabled that anecdotally example that lifted the tides of adjacent communities that don't rely on Ghostty technology at all. I didn't predict this. Make things better because they can be better and let the results naturally play out.

@thsottiaux Keyboard navigation. A quick fuzzy search for chats.

What is something that you feel is surprising that Codex still can't do well and we should have gotten right a while ago?

@github u good dawg?

We heard you. And we agree. In light of recent developments in physical media, GitHub is proud to announce that you can now obtain your public repo on CD-ROM. Keep it. Lend it to friends. Pass it on to your children. Your code is physically yours, forever. Until you lose it, let's be real. Order yours today. gh.io/cd

@ThePrimeagen This is my only issue with 5.5 / 4.8. They're fine for what I need, I just need to type "ok do it" so many times. /goal not much help. Ultracode good but takes forever. Fable is the only one that follows through, output doesn't feel meaningfully different (for my needs)

20% of my time with an 5.5 is saying: "Did you do it?" ... "Ok then do it"

@zeeg xHigh great for review and planning/exploring assistance. I'd never use it to implement things.

so what is fable good at besides consuming large amounts of time? i mean this as a serious question, because i dont want to spend hours waiting on sessions (and $$$$) to find out the task at hand it performed ~same as gpt 5.5

@NikoStarus @neetcode1 Main thread xhigh orchestrator. Fable5 medium workers, high reviewers, orchestrator (xhigh) final pass review. Did use Opus 4.8 xhigh workers for some code I knew would be trivial.

@azegallo @neetcode1 Bro hoowwwww I did the same and hit my 5 hour limit in 30 mins lmao

how are you guys hitting your usage limits? I can barely get a prompt to finish within 10min on Fable

Hey Fable 5, /loop wake me up when GPT-5.6 is here 🥱

@AnthropicAI "Tomorrow"

Claude Fable 5 will be available again globally tomorrow. After a series of productive conversations with the US government, we're redeploying the model with a new set of classifiers to target and block more cybersecurity tasks. In the near term, some routine tasks like coding and debugging will fall back to Opus 4.8. We’ll continue to refine these classifiers over the coming weeks to reduce false positives and better distinguish genuine misuse from legitimate requests. We’ve also begun drafting a consensus framework—with Amazon, Microsoft, Google, and other Glasswing partners—for assessing the severity of AI jailbreaks and how AI developers should respond to them. We invite other industry partners and model providers to join us in this effort. Finally, we’re scaling up our collaboration with the US government on model testing and safeguards. This will include pre-release access to models and safeguards for evaluation, information sharing on jailbreaks and misuse, and dedicated resources for joint research. Thank you to our users for your patience, and to our partners across the government, industry, and the research community who worked alongside us to make Fable 5 available again. Read our full blog: anthropic.com/news/redeployi…