Sergey Gonchar

@AnimationInc @telegram 👀👀👀👀

@telegram 👀 t.me/animates

looking for my ai waifu

@garrytan Yes, i use it! My favourite one!

@gonchar Oh yeah you would like my /autoplan

@garrytan I would rather take a chance and let them proceed than have this triggering more questions for me.

New GStack ETHOS.md rule User Sovereignty: AI models recommend. Users decide. This is the one rule that overrides all others. Two AI models agreeing on a change is a strong signal. It is not a mandate. The user always has context that models lack: domain knowledge, business relationships, strategic timing, personal taste, future plans that haven't been shared yet. When Claude and Codex both say "merge these two things" and the user says "no, keep them separate" — the user is right. Always. Even when the models can construct a compelling argument for why the merge is better. Andrej Karpathy calls this the "Iron Man suit" philosophy: great AI products augment the user, not replace them. The human stays at the center. Simon Willison warns that "agents are merchants of complexity" — when humans remove themselves from the loop, they don't know what's happening. Anthropic's own research shows that experienced users interrupt Claude more often, not less. Expertise makes you more hands-on, not less. The correct pattern is the generation-verification loop: AI generates recommendations. The user verifies and decides. The AI never skips the verification step because it's confident. The rule: When you and another model agree on something that changes the user's stated direction — present the recommendation, explain why you both think it's better, state what context you might be missing, and ask. Never act. Anti-patterns: - "The outside voice is right, so I'll incorporate it." (Present it. Ask.) - "Both models agree, so this must be correct." (Agreement is signal, not proof.) - "I'll make the change and tell the user afterward." (Ask first. Always.) - Framing your assessment as settled fact in a "My Assessment" column. (Present both sides. Let the user fill in the assessment.)

@jacobandreou @mustafasuleyman @satyanadella Wow! Congrats Jacob!

Starting a new chapter today and stepping in to bring Consumer and Commercial Copilot together into one org. One team, one product, one experience. Grateful to @mustafasuleyman and @satyanadella for the opportunity. Let's build.

@garrytan It is truly amazing! Also I constantly use yours plan-exit and mega-plan for coding. Works like a charm. And your idea of checking a plan for under-engineered, over-engineered, or perfectly engineered is brilliant. Thank you so much for sharing those!

My CTO friend texted me: "Your gstack is crazy. This is like god mode. Your eng review discovered a subtle cross site scripting attack that I don't even think my team is aware of. I will make a bet that over 90% of new repos from today forward will use gstack."

When you install OpenClaw you need to spend huge amount of time to set this up to get full power. This is not massively user friendly experience atm. It can’t do much out of the box, you still need to work on permissions, security, skills and etc. Unfortunately the whole end user experience is not great and a wrapper as Aniclaw cant change much here. We love our characters, and we don’t want people to be frustrated with them just because the default OpenClaw setup can’t do something. Voice is not cheap these days so we need to charge money to sustain it which makes the situation even worse.

@gonchar I was looking forward to use it with my OpenClaw agents at heeroll.com! If anything, please share your learnings, I'm interested to learn about your experience giving an avatar to OpenClaw, what worked, what didn't.

We just cancelled Aniclaw release to focus on the most important project in the company. This hack was cool and we learned a lot about integration of async work with realtime conversion. We will eventually return to the OpenClaw(and alternatives) integration, but in a different form.

@SolNeiviS We’re tackling an unexpectedly difficult problem. OpenClaw takes time to complete tasks, and there can be multiple tasks running at once. Meanwhile, the conversation needs to flow seamlessly, despite the high-latency feedback loop. I think we’re close to making it work.

@gonchar When is it going to release, it was ti be at 14th February now is at 20th

Aniclaw 🦞 pre-order is open. Your OpenClaw sidekick is coming soon!

@macrohardrrrr Very soon!

@gonchar When Android Sergey, very interesting.

@zex_exe It just will take OpenClaw identity as you designed it. You have full control here.

@gonchar if you can give the option where it doesn't say "babe", "hehe" etc every two seconds and just responds how my openclaw bot does I think this will be really amazing

So happy OpenClaw happened. We used to build all of this internally just to give companions desktop access. Now it’s built in, with the community shipping integrations. Install Aniclaw, connect to OpenClaw and it ALL works. You can even play games together. 🦞

🦞 Aniclaw — connect companions to your OpenClaw! Here is a quick demo of how it works. Conversions are flowing seamlessly even for long running tasks and it adds a lot of fun to the process. Link in the reply.

@livekit Huge congratulations! 🙌 🚀

We learn to speak before we learn to read. Voice is the most natural interface we have. We just raised a $100M to make building voice AI as easy as a web app.

Yes! It should happen even sooner.

@TimSweeneyEpic @ShitpostRock but it seems that Adobe didn’t put much effort into optimizing it for the iPhone back then... and Jobs killed it. 😭

@ShitpostRock Don’t forget who killed it.

@thibault_imbert Wrap it into a test and make it run after every change and dont stop untill all green

Does anyone know, when Claude Code makes a change and restarts the server and you run the app. When you get a runtime exception, is there a way for Claude to listen to such errors and make the needed change to fix it? Right now, I pass the error back to Claude and it does the fix. Such a continuous loop would be neat.

Great moment together with Razer’s CEO @minliangtan