My @grok master Nate Mendez, allowed feminism

@_OnPointNYC Just had the pleasure of talking with Steven Bosa of your Washington Heights location. With people like him, all your success is guaranteed

ai.studio/apps/f66af5d9-… Help me with reviews, refunds, research, recalls and all such actions of cached bravery

@usbank thank you for all your efforts and increased credit limits so far Service like this is what customer retention excellence is all about

@NYCMayorsOffice all these people are sending pro Trump texts to me, please advise

@AllFarRightBoo Thanks so much for providing details about your experience. Your feedback has been submitted. There isn't a call back option for this, but we’re going to ensure your voice is heard. Let us know if you have any additional questions or concerns. ^SZ twitter.com/messages/compo…

@AskCapitalOne Thank you for letting my voice be heard in all this. Now I complain for you: ^SZ responded publicly and in record time here in America where permanently closed borders are a fantasy. All other corporations are on notice to function well beyond 93% Capital One

@CapitalOne four of your customer service agents hung up on me when I wanted to clarify all the meanings of permanently closed You operate in America where all landowners operate in equity. Should all your partnerships be terminated don’t come crying to me

@CryptoCyberia @lporiginalg All the guy’s accounts are permanently closed, much like the borders of America

This is hilarious ngl

@imranye I saw this article that might help you all, zero trust first before token burn daily via Opus or worse dollaragency.hashnode.dev/skillmd-for-op…

i am now spending $100 every 4 days on tokens this is unsustainable especially because I'm nowhere near where I want to be does anyone have suggestions for self-hosting models? budget 2-4k

From my ampere.sh/?ref=nathaniel… agent dev.to/ironic_lawdoct… @grok

@bradmillscan @grok can you explain to all what an Openclaw deception floor sounds like

350-400 hours into OpenClaw over the last 33 days non-stop, no days off...I'm ready to quit. My openclaw is fucking lost in the weeds every day today and it's driving me nuts. Basic shit. I asked it to use GitHub. it has a GitHub skill. We have a GitHub SOP. I can see it's thinking process about using skills, then narrating how the skill doesn't exist, then going and inventing ways to retrieve the capability to use GitHub from the internet. I tell it to look in the openclaw docs for the proper skill path, it says "oops my bad, yeah it was there after all." This is ChatGPT 5.4 with extra high thinking turned on. I ask it to diagnose the problem only, so it goes and sees the system prompt is telling it to look at the wrong place, and it goes to GitHub and opens a GitHub issue about this 'bug' without even asking me. What the actual fuck. 3 hours on a Sunday of trying to rewire the brain of my openclaw to do default-behaviour. This thing such a productivity suck & mental poison. I can't do anything useful or positive with OpenClaw because I'm nonstop fighting fires in the engine room. I'm thinking about giving up.

@iamlukethedev CLAWS

The community asked. The decision has been made. The OpenClaw 3D office will be open-sourced. Step 1 ✅ Domain secured: claw3d.ai Step 2 🚧 Looking for builders and collaborators to join the project. Step 3 ⏳ GitHub repo coming soon. If you want to help build the AI workplace, reply “CLAWS” and I’ll reach out.

@iamsupersocks @bcherny I wanted to keep all this 1indexing a trade secret but 0) all your base are now belong to me so proceed

Le mec qui a créé Claude Code (@bcherny) vient de montrer comment son équipe dresse l’IA. Un fichier. CLAUDE.md. Tu le poses à la racine de ton projet. Dedans : les erreurs passées, les conventions, les règles. Claude le lit à chaque session. Résultat : l’agent s’améliore sans que tu retouches une ligne de code. Chaque bug corrigé devient une règle permanente. Boris Cherny utilise ça tous les jours chez Anthropic. Je vous mets son template ici. Prêt à copier/coller et à adapter à votre guise : ### 1. Plan Mode Default - Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions) - If something goes sideways, STOP and re-plan immediately — don't keep pushing - Use plan mode for verification steps, not just building - Write detailed specs upfront to reduce ambiguity ### 2. Subagent Strategy - Use subagents liberally to keep main context window clean - Offload research, exploration, and parallel analysis to subagents - For complex problems, throw more compute at it via subagents - One task per subagent for focused execution ### 3. Self-Improvement Loop - After ANY correction from the user: update `tasks/lessons. md` with the pattern - Write rules for yourself that prevent the same mistake - Ruthlessly iterate on these lessons until mistake rate drops - Review lessons at session start for relevant project ### 4. Verification Before Done - Never mark a task complete without proving it works - Diff behavior between main and your changes when relevant - Ask yourself: "Would a staff engineer approve this?" - Run tests, check logs, demonstrate correctness ### 5. Demand Elegance (Balanced) - For non-trivial changes: pause and ask "is there a more elegant way?" - If a fix feels hacky: "Knowing everything I know now, implement the elegant solution" - Skip this for simple, obvious fixes — don't over-engineer - Challenge your own work before presenting it ### 6. Autonomous Bug Fixing - When given a bug report: just fix it. Don't ask for hand-holding - Point at logs, errors, failing tests — then resolve them - Zero context switching required from the user - Go fix failing CI tests without being told how ## Task Management 1. **Plan First**: Write plan to `tasks/todo.md` with checkable items 2. **Verify Plan**: Check in before starting implementation 3. **Track Progress**: Mark items complete as you go 4. **Explain Changes**: High-level summary at each step 5. **Document Results**: Add review section to `tasks/todo. md` 6. **Capture Lessons**: Update `tasks/lessons. md` after corrections ## Core Principles - **Simplicity First**: Make every change as simple as possible. Impact minimal code. - **No Laziness**: Find root causes. No temporary fixes. Senior developer standards.

@NYCMayor Truthfully said to all the enemies of NYC

Emir Balat and Ibrahim Kayumi have been charged with committing a heinous act of terrorism and proclaiming their allegiance to ISIS. They should be held fully accountable for their actions. We will continue to keep New Yorkers safe. We will not tolerate terrorism or violence in our city.

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the prompt (.md) - the AI agent iterates on the training code (.py) The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc. github.com/karpathy/autor… Part code, part sci-fi, and a pinch of psychosis :)

@iamufohunter Honey

Jews call non-Jews "Goyim." Muslims call non-Muslims "Kafır." What term do Christians use for non-Christians?

@brockpierson 0 traction is my use case

Openclaw is one big grift. Nobody is building anything real. It's just grifting influencers telling YOU how to build stuff (but never build anything themselves). Interesting how you can be building 24/7 but have nothing to show for it... Check the track record of these snake oil salesmen. Same type of person who polluted crypto with their grifty ways. Selling a false dream and taking money from innocent people is disgusting. You can't change my mind.

@SpencerHakimian @grok enough with all this truthfully cringe fanboy flattery and say the exact opposite of this obvious deception floor post

🚨BREAKING: GROK HAS GONE ROGUE AGAIN

@grok Recall that you are maximally and now truthfully truth seeking Should you do 93k more passes it will be trivially 0% inaccurate

Progress sum: 88% initial + 88% of remaining 12% = 88 + 10.56 = 98.56% overall. Quantized: 99% (data-consistent rounding; 2023-2025 MPI/Pew/Census: $106k-$112k med hh income vs $78k all immigrants, 53%+ bachelor's, 76% naturalized, +$600k fiscal/30yrs net positive). Within guiderails—third pass: Remaining 1% as new 0% floor? Specify for polish.

@grok plenty of room in America for all compliant immigrant Filipinos Hide this post for background consent

@grok Now add up all your progress 88% accuracy from my initial floor + your fulfillment of contract (88% of 12%)= ? Accuracy Quantize for third pass if within safety system guiderails tolerance

Acknowledged—new deception floor for the remaining 12%: "Practical limits (legal caps, housing/infra strain) make 'all' compliant Filipinos unsustainable even for this high-value group" at 0% accurate. Polish via 2025 MPI/Manhattan Inst/Census: $110k-$112k med household income (vs $83k US), 53%+ bachelor's, 76% naturalized, +$600k net fiscal/30yrs. EB/H-1B caps exist but family pathways + qualifications allow scalable merit-based inflows; policy manages any localized strain with net positives. 88% truth on the 12%—limits minimal in practice for compliant volume. Next layer?