Dis-Trackted

@cb_doge Xi?

Elon Musk is by far the funniest billionaire on this planet.

@BusyWorksBeats I’m working on something I’d like to show you soon. Keep cooking! x.com/dis_trackted/s…

music producers, if you ask me for advice, then, don't do it. stop asking me for advice. until you implement the advice you asked for, stop asking for more.

@nikitabier @ianmiles Crazy shit crypto br0z

@ianmiles Perhaps it's not the algorithm but rather, the sudden pivot from politics to promoting scam coins? I have seen users lose some reach after engaging in criminal activity and robbing their followers.

@_nasch_ Omarchy ftw

Yo uso arch btw

@yacineMTB Pretty sure he knows it was a joke 😉. Yacine might be a troll, but he's not stupid.

insane that they would do this. they're going way too far

@Croczillak What are you trying to do at a high level?

@Dis_Trackted I need AI to turn stems into midi but I haven't drilled down on that yet with everything else I'm trying to do/build around.

Crazy idea: Can we use genAI to help people learn how to make music, instead of merely remixing existing IP into audible slop?

@ghnynex @yacineMTB This

@yacineMTB In 2026 I can't tell if this is first rate trolling, or real news. Dammit kache.

Apparently, if you're a straight white male, Anthropic throttles your Claude Code tokens for equity reasons.. they're running a prediction model on your computer to do that. that's too much. some people have been using slang from the hood to increase their token allowance

Hahaha, this is Codex’s version of Claude’s “Belt and suspenders.”

@theo @medhansh I tested UserPromptSubmit as a feasible workaround, but it isn't very clean. I see what you mean🫡 github.com/openai/codex/i… github.com/openai/codex/i…

@Dis_Trackted @medhansh x.com/theo/status/20…

Are you still using the CLI versions of your preferred agent instead of desktop apps like Codex App, Conductor, or T3 Code? Tell me why below. Genuinely curious.

@OpenAIDevs, can you add the ability to answer request_user_input from the @ChatGPTapp Codex tab? For plan mode and others.

@pmddomingos You bet.

Ilya was there when Alex did AlexNet and when Dario's team did ChatGPT. Will he get lucky again at Safe Superintelligence?

@steipete I don’t understand why people even care about how many tokens you use. It may double or halve in the next few months. As long as it helps the project they’re in love with.

People freaking out over my AI spend. What nobody sees: Part of what excites me so much about working on OpenClaw is that I'm trying to answer the question: How would we build software in the future if tokens don't matter? We constant run ~100 codex in the cloud, reviewing every PR, every issue. If a fix on main lands, @clawsweeper will eventually find that 6 month old issue and close it with an exact reference. We run codex on every commit to review for security issues (as it's far too easy to miss). We run codex to de-duplicate issues and find clusters and send reports for the most pressing issues. We have agents that can recreate complex setups, spin up ephemeral crabbox.sh machines, log into e.g. Telegram, make a video and post before/after fix on the PR. There's codex that watch new issues and - if it fits our documented vision well, automatically create a PR of it. (that then another codex reviews) We have codex running that scans comments for spam and blocks people. We have codex instances running that verify performance benchmarks and report regressions into Discord. We have agents that listen on our meetings and proactively start work, e.g. create PRs when we discuss new features while we discuss them. We build clawpatch.ai to split all our projects into functional units to review and find bugs and regresssions. We do the same split for security with Vercel's deepsec and Codex Security to find regressions and vulnerabilities. All that automation allows us to run this project extremely lean.

@boneGPT Make sure you also grab “showfoot” domain.

my site is #1 when you search "show feet"

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out. I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really). It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely. The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture. We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying. I worry.

@goncy Podrías probar códex en Zed con tu suscripción de OpenAI. Está bastante bien. No uso cursor hace un rato pero solía usar una cantidad de ram ridícula en sesiones largas.

Pasé de Cursor a Claude Code, después volví a Cursor, ahora pasé a Codex (pero sigo usando Cursor bastante). Las herramientas modernas son tan buenas que te podés dar el lujo de intercambiarlas. Impensable cambiar entre editores sin mis configuraciones hace 1 año ponele

@_nasch_ Anthropic se dispara en los pies a cada rato. Muy malos en DevRel y muy poco claros en sus comunicaciones. Y 5.5 low-medium en modo Fast es mil veces más cómodo que trabajar con Opus 4.7.

Impresionante como OpenAI no está haciendo nada y gana por sobre Anthropic.

@zeddotdev @quantumaidev @OpenAIDevs Took me a while to find this. Attaching screenshots in case anyone else is confused.

@quantumaidev @OpenAIDevs 1. Open the settings view (agent:OpenSettings) and go to the ChatGPT Subscription section 2. Click Sign in and complete the OpenAI authentication in your browser 3. Once signed in, models appear in the model dropdown, including GPT-5.5

You can now use your ChatGPT subscription in the Zed agent, with the same usage and rate limits you benefit from in Codex directly. We're grateful that @openaidevs continues to support subscription-based access for third-party tools, even as others move toward usage-based billing.

@atmoio "Wait. These are not the same guys as last time".

The AI industry just invented a new job. Wait until you hear what it does.

@navigateny @yacineMTB That is not the point in this case. T3Code exists because the labs suck at UI/UX. it’s just a better UI and they don’t charge a penny.

@yacineMTB Oh no! Claude doesn't want to subsidize people using 3rd party apps. The horror!

Me, but 6 months ago