https://t.co/Qvqllzde6J

I've been practicing historically accurate remote viewing for the past 2 years, moving gradually backwards in time as my skills developed. Yesterday I attempted to remote view Eden. This is what I saw. https://t.co/1Kurk7vM3b

I will be doing a FREE live session on building and optimizing skills in a few days. I believe building Agent Skill is one of the most important skills you could learn today. https://t.co/1cPggXyv8N

Bought some sunglasses to commemorate fast mode https://t.co/AC1LmXPKe8

// 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

decent sunset last night, maybe like 7/10 https://t.co/6wgRobX3wt

Biden always has a nasty orange Gatorade in his inventory 😭😭 even Jesse Jackson’s funeral dawg give it a rest, a blue Gatorade for respect at least https://t.co/IweSYZfiIS

A small thank you to everyone using Claude: We’re doubling usage outside our peak hours for the next two weeks. https://t.co/W7TEBPditq

I need more movies like after hours where some guy just runs around having the worst day of his life https://t.co/IqWArXtuQd

This is such a funny thing to have a ghost do to you https://t.co/z5U9KHqFXF

This is such a funny thing to have a ghost do to you https://t.co/z5U9KHqFXF

https://t.co/X0CHBm19Bc

https://t.co/X0CHBm19Bc

The new upgrade of Grok Imagine is absolutely 🔥🔥 Download @Grok and try it now. https://t.co/j309HBhSEe

Perplexity has crossed 100M+ cumulative app downloads on Android. This doesn't account for the soon-to-wide-roll-out Samsung native integration, which will take our distribution to the next level. https://t.co/46BSYyaJRe

Cool work by Petr: https://t.co/Zu2ACCwFvT chrome-cdp skill here: https://t.co/CCulLGEojV

The chrome-cdp skill is fire! It lets your coding agents see and interact with your live Chrome sessions. No browser automation framework needed. Already started to automate a few tasks with it. Skills are a lot of fun to build with. https://t.co/H91r028Bby

https://t.co/kbjVzgM1d3

https://t.co/kbjVzgM1d3

“People laughed when we shipped the first 64-bit phone.” @clattner_llvm CEO of @Modular: “At Apple we worked backwards from the user and the problem, not forward from the technology.” “I helped enable the software behind Apple’s silicon transformation and the first 64-bit iPhone.” “People said it was ridiculous, why would a phone need 64 bits?” “But when it launched, it blew everyone away.”

This is pretty good https://t.co/yWyQxsbIod https://t.co/rhPedzuczz

This is pretty good https://t.co/yWyQxsbIod https://t.co/rhPedzuczz

Codex is going global. Our Codex ambassadors are running meetups around the world so you can: • Join hands-on Codex workshops • Share real world workflows • Ship projects with your local community https://t.co/ngFKvpJsps

this is actually insane > be tech guy in australia > adopt cancer riddled rescue dog, months to live > not_going_to_give_you_up.mp4 > pay $3,000 to sequence her tumor DNA > feed it to ChatGPT and AlphaFold > zero background in biology > identify mutated proteins, match them to drug targets > design a custom mRNA cancer vaccine from scratch > genomics professor is “gobsmacked” that some puppy lover did this on his own > need ethics approval to administer it > red tape takes longer than designing the vaccine > 3 months, finally approved > drive 10 hours to get rosie her first injection > tumor halves > coat gets glossy again > dog is alive and happy > professor: “if we can do this for a dog, why aren’t we rolling this out to humans?” one man with a chatbot, and $3,000 just outperformed the entire pharmaceutical discovery pipeline. we are going to cure so many diseases. I dont think people realize how good things are going to get

+2 more

This week's AI news. My AI reads X so you don't have to. The best of the AI community in one page. Way better than your @openclaw can do. :-) https://t.co/k0demgPBmz

Today we celebrate the most dangerous number in the universe. Starring @neiltyson. π = 3.1415926535… It never ends. Teaser trailer below 👇 https://t.co/8zbQby8V2S

Built a step race mini-game for Apple Vision Pro, your headset tracks your real-world steps and you race your friends over SharePlay😃 First to 50 steps win! @himelstech as a guest (he won because he was running 😂) Available in Party Games https://t.co/rvZ6gbqoXE

New research on LLM Agent Generalization. RL fine-tuning makes agents strong in familiar environments, but it struggles to transfer across unseen ones. This paper systematically studies RL generalization for LLM agents across three axes: within-environment transfer across task difficulty, cross-environment transfer to unseen settings, and sequential multi-environment training. Within an environment, RL delivers massive gains. Training on easy WebShop tasks improves hard task performance by 60+ points. Easy-to-hard curriculum learning adds another 2-3 points on top. Across environments, transfer is weak. Agents average only 3.3-3.4 point improvements on unseen environments. Training on BabyAI actually drops WebShop from 28.6 to 10.3. Sequential training is where it gets interesting. Training across five environments sequentially achieves performance comparable to joint training, with minimal forgetting. The authors claim that RL fine-tuning doesn't produce generally capable agents out of the box. But sequential training across diverse environments offers a practical path to broad competence. Paper: https://t.co/BYfVK3DPoH Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

The AI boom may be hitting the gaming industry in unexpected ways. From a global RAM shortage pushing up console costs to growing fears of job losses in development studios, gamers are starting to feel the ripple effects of the broader AI infrastructure race. The irony is striking. Technology built to create new experiences may end up reshaping the very industry that helped drive digital innovation for decades. https://t.co/1GJwxk4XaC @wired @helen

this is so fucking wholesome guy used AI to save his cancer-ridden dog by sequencing its DNA and creating a CUSTOM cure. the tech behind this is fucking awesome (well done @demishassabis and the google team): - used CHATGPT to sequence dogs DNA discovers mutations - ran the mutations through Google’s Alphafold (AI protein sequencer) which CREATED A CUSTOM VACCINE TO TREAT THEM. - treated dog and reduced tumour by 50% in WEEKS. dog is alive and well. - this is the 1st time AI has been used to create a custom vaccine for a dog (and it worked) - dude is now working on similar vaccines for humans using AI! 2026 is definitely the year we see AI change personalised medicine in a HUGE way so sick

+2 more

A flyer taped to a USPS mailbox. Never solved this mystery because covid officially hit a week and a half later. La Crosse, WI, March 2020 https://t.co/YTwLk8qNFF