Libegato

@iamerickdamon @zachrip_ @thdxr @DeLsonJabberwo What’s the difference between a new random id and the actual user id? Opencode still need to store it linked to the user. You’re asking for some Telegram thing that a common company won’t do

@Libegato @zachrip_ @thdxr @DeLsonJabberwo yeah u're right. probably just a random identifier would suffice then, not real user id that openai can query into if they somehow have access. i mean, put some effort into privacy.

when gpt 5.3 codex came out they had a new process because they were worried about cyber abuse we pass through user IDs to them so they can block bad actors easily - and we see a ton of blocks if only they thought to do a whole marketing video on it

@iamerickdamon @zachrip_ @thdxr @DeLsonJabberwo How would a block work if they changed the ID every month?

@zachrip_ @thdxr @DeLsonJabberwo > how is it different yeah probably need to do a bit of extra work like changing it every month etc, let's not go into technicality. My point is just that I care about privacy. > There is no privacy intrusion we don't know for sure 🙂

any suggestion of markdown readers? It's weird to have to open vscode to read a .md generated by an LLM. Also my terminal windows are usually small, so nvim even thought with formatters isn't what I expect

Me prompting my coding agents at 3am

@NickADobos Ops, T3 Chat, not R3

@Libegato I mean. This would allow other harnesses to work cuz you could just wrap it in the harness. So it defeats the entire purpose???

Isn’t this impossible to enforce unless they remove a significant portion of Claude code? claude -p <prompt>

@NickADobos I think openclaw and related tools were exploiting auth like that Opencode plugin was.. keeping under actually Claude Code harness (you won’t call Anthropics API directly, Claude Code will) reduce their unwanted usage. R3 Chat is doing it. Recent Cline Kanban too

@levelsio Me

Okay and who of you couldn't reply to this? Please please only if you couldn't okay?

@VictorTaelin Hey Taelin, what about that Mac Mini cluster? Now that you have powerful verification tools (bend etc), not-so-sota will perform better

I just realized that, for the first time ever, progress on both HVM and Bend is bottlenecked not anymore on time, and not on my own knowledge, but on money. I could, right now, be throwing thousands of agents on the repos, with well crafted prompts, and progress would accelerate 10-fold overnight. I know "my agent is outputting 100k lines of code" is a silly meme, but it does apply here. Bend is now equipped with everything it needs to convert agent time into real progress, at any scale. This weekend I validated that, leaving agents working on the standard libraries overnight, and I woke up to thousands of lines of well written, tested, verified code that just worked. One of the agents even started implementing a 3D rendering library in Bend, and it got incredibly far! So, if I can trade money for having ThreeJS in Bend's ecosystem overnight, I think it is not a stretch to say we could port nearly anything to its libraries very quickly. Now, of course, our budget is limited; currently, this is all running mostly with a few agents under a single personal Codex/Claude subscription. But what is preventing me from just throwing, say, 10k on it, and checking what they create, and how far the go? Nothing, and I think this is the next step. It is worth noting that progress here isn't in the "solving new problems" sense; they are not creating anything "new"; they are just implementing existing things in a new language. But that's exactly the "Bend ecosystem is small" problem I'm trying to solve right now! Seems like AI was made for this

claude code down?

@LLMJunky Sourced != Curated, right?

Now that Subagents are officially GA, I have a gift for you. An enormous library of 425+ custom agent roles that you can drop directly into Codex. Subject matter experts of all kinds, curated from across Github. Link in the comments 🔗 Stars appreciated

Hey @VictorTaelin I’ve heard some buzz about “quint lang”. Is it something from the same domain of Bend/HVM etc?

@justalexoki Human verification

why would Meta want online age verification so bad they spend $2 BILLION dollars on it??

@rolayfamous @CollinRugg @grok Interviewing for a job 😆

@CollinRugg @grok why they have name tag on the beach?

@Dimillian Jesus, mate

18 billions tokens

Hooks are coming to codex. That’s all I wanted to say.

Wild times

@Galaxy01500 Couldn’t they already? Shadow accounts?

@arvidkahl Most popular is not 100%, right? Are most of iOS US folks using Chrome, for example? I use Safari.

If you even test your web app in anything but Chrome, you're effectively optimizing for Equatorial Guinea.

@yacineMTB How’s it on the other side?

To clarify, both manually and with an LLM. I have not produced any code natty or otherwise

it has been 3 weeks since i have written any code at all