Your curated collection of saved posts and media
A quirky new trend is sweeping China’s AI scene. “Raise a lobster” style OpenClaw agents are going viral, turning autonomous AI tools into the latest experimentation playground. Behind the hype lies something bigger: a rapidly evolving ecosystem pushing the boundaries of agentic AI. https://t.co/WrQqG6qcuG @nickrigordon @fortunemagazine
// Continual Learning from Experience and Skills // Skills are so good when you combine them properly with MCP & CLIs. I have found that Skills can significantly improve tool usage of my coding agents. The best way to improve them is to regularly document improvements, patterns, and things to avoid. Self-improving skills don't work that well (yet). Check out this related paper on the topic: It introduces XSkill, a dual-stream continual learning framework. Agents distill two types of reusable knowledge from past trajectories: experiences for action-level tool selection, and skills for task-level planning and workflows. Both are grounded in visual observations. During accumulation, agents compare successful and failed rollouts via cross-rollout critique to extract high-quality knowledge. During inference, they retrieve and adapt relevant experiences and skills to the current visual context. Evaluated across five benchmarks with four backbone models, XSkill consistently outperforms baselines. On Gemini-3-Flash, the average success rate jumps from 33.6% to 40.3%. Skills reduce overall tool errors from 29.9% to 16.3%. Agents that accumulate and reuse knowledge from their own trajectories get better over time without parameter updates. I have now seen two papers this week with similar ideas. Paper: https://t.co/YXrHcJ6Zim Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX
@bcherny @0xPaulius Account settings, some settings like privacy are already there and propagated. Could be also default model and more.
@VladTheInflator The fact they know this and don’t care should make us wonder what their actual plan is
@aiktp_com Merch for sale. Tesla perigee are also SpaceX fanatics.
in the next claw release (~Sunday), you can always ask your agents, even they are busy working. https://t.co/TVX9o6ciKo
Shot this picture at dinner. But the important thing is soon you can talk more to your claw. So your AI works better with you. https://t.co/VTgfLSkUFV
Elon’s dream might seem ridiculous. And it is. In today’s context. This will require all billionaires to share with everyone. Chances that would happen? Not very likely. But we should put together a pitch to try to convince them. A group of them meets for lunch in Dallas every month. I bet we could get a slot if our pitch was good enough. What do they get in return? How about a statue in Times Square to start? I believe we could convince them. Or at least enough of them to try a few things together. I watched the founder of @stoke_space pitch this particular lunch group in Dallas a couple of years ago. A friend invited me who is always invited to this lunch. He pretty much made that kind of pitch to get his rocket company to the next stage. Slightly different: his pitch was to save their lifestyles by building defenses against hypersonic missiles. And it worked. By the way, hey Elon does talking to an AI all night constitute “a job?” I believe it does. I built a new way to read X by doing so. Will turn that on real soon now. Brayden and I are meeting in the morning to see if we can launch it this week. My new job is talking to AIs and in my case it is voluntary. Put my own money into it. If it brings me a high income I will be impressed. I don’t expect it to survive long. If I can build such a thing an engineer at X can too. Hey @grok does @nikitabier still hate lists? Prediction: he won’t after he sees what my AI did with them.
Meta is reportedly building its new AI unit with ~50 engineers per manager. That ratio might work in a data center. It rarely works in a research lab. AI breakthroughs don’t come from scale alone. They come from tight feedback loops, fast decisions, and strong technical leadership. Does extreme scale accelerate innovation or slow it down? https://t.co/VEAa7Nttot @fortunemagazine @clairezillman
@LingoUnbound https://t.co/cPIsHUE9wh
@LingoUnbound got it all figured out 👌🏻
@BarnabustGridly @Srirachachau nice
The #GenAI & Multimodal track at #PyTorchCon Europe explores building & scaling generative & multimodal models using #PyTorch. Learn more: https://t.co/5Eh1Rj2BEl 🎟 Register → https://t.co/FXnQdW5qwy https://t.co/fjtQ2HNlNA
Researchers are starting to examine the psychological risks of constant AI interaction. A new study warns that chatbots may reinforce delusional thinking in vulnerable users, raising concerns about what some call “AI psychosis.” As AI becomes a daily companion for millions, understanding its mental health impact is becoming urgent. https://t.co/q8YK6Xbjlb
Built an app that teaches Braille through touch for Apple's Swift Student Challenge 2026. Drag your finger across a dot grid and your phone buzzes hard on active dots, soft on inactive ones. your hands learn the pattern before your brain does. AR Tutorial Mode puts a ghost hand on any flat surface through your camera and guides your finger dot by dot. Camera scanner converts any real-world text to Braille instantly. full VoiceOver and Siri support. 250 million visually impaired people. an iPhone already has everything needed to help. 20 year old dev from India. built this because the problem was real. full video walkthrough here: https://t.co/iNG2ypAGLA want to try it yourself? drop a comment and I'll share the link
next show!!! https://t.co/km3z3a0XUj
this guy vibe coded an AI SURVIVAL APP that works COMPLETELY OFFLINE the app > gives you survival advice completely offline > cites exact pages from manuals stored on the device > has offline maps so you're never lost > lets you text people up to 50 miles away with no cell service it started off as an app but now he's selling physical devices it's waterproof, under 3 pounds, and strong enough that you can run it over with a car the app hit 14k users and became the world's #1 rated survival AI which is insane
cancel your chatgpt subscription and delete your openclaw slop. i'm serious. go on ebay and buy a used RTX 3060 for the price of two months of pro. or check your drawer because half of you already own one and forgot about it. install hermes agent from @NousResearch. one framework, 31 tools, file operations, terminal, browser, code execution. connect it to your local llama.cpp server running qwen 3.5 9B Q4. total download is 5.3 gigs. that's it. that's the whole setup. every experiment you hesitated to run on API. every project you shelved because you didn't want your data on someone else's server. every late night idea you didn't test because you hit your rate limit. all of that is gone. runs 24/7 on your electricity. your machine. your data never leaves your house. connect it to telegram if you want it on your phone. hook up whatever tools you need. the model thinks at 29 tok/s with 128K context and it never bills you. qwen 3.5 9B and one RTX 3060 is the setup most people will never try because they've been trained to believe intelligence has to come from a datacenter. it doesn't. it runs on 12 gigs of VRAM under your desk right now. stop giving your thinking away for free.
The planet Saturn, captured during it's closest approach to Earth from the top of a parking garage in the heart of Los Angeles. You can do plenty of astrophotography from a big city! https://t.co/bhR2kWAJ4p
Fired USAID Employee In Charge of Making Countries Gay Speaks Out https://t.co/wFnj3WlhyO
Evolution of the Taxi https://t.co/DpVJ69Kud1
