Stop calling simple LLM calls „Ai Agents“. They‘re not. LLM = a powerful brain 🧠 Agent = The brain in a body, with tools, memory and a mission Big Difference, one answers questions, the other completes tasks

How can free speech differentiated from misinformation?

Either the EU plays 4D chess and in a couple of decades/centuries we will come out on top. Because we have forcefully invested (incentivized) inevitable but not contemporary ideas. Like privacy, EV, Renewable Or This is mostly ideology Which destroys our economies

Europe is so back. No more cookie banners, if member states approve of the proposal. theverge.com/news/823750/eu…

there are 4 seasons in a year openai google anthropic *you are here* china

"Sorry" for the lack of posts. I’ve been busy with this. 👇 Current status at MEETYOO: • Full dedication to the code (yes, even as CTO). • 10+ hidden features in the works. • Zero "vaporware". We don't build for the hype. We build for the customer.

Unpopular opinion: Multi-agent "swarms" are often just technical debt in disguise. We tried the Planner > Executor > Replanner architecture. It was a hot mess of hallucinations and loops. We switched back to a single, high-capability model. It outperformed the swarm immediately.

Css anchor is around the corner. Finally one of the most anticipated APIs in the web. I guess Jake Archibald is to he thanked for the FF support.

AI agents need data, but you can't let them run wild in your production database. Our solution: A secure, in-flight sandbox. The agent can now explore, analyze, and visualize customer data autonomously and safely.

I always thought putting 2 of the same icons next to each other is bad UX. Well I‘m definetly confused. Always press the wrong (X) … liquid (gl)ass

Two massive deals: OpenAI's $1B Disney IP grab for Sora + Netflix's Warner Bros bid. Why? AI video abundance is here. Attention is scarce—IP is the ultimate moat for beloved slop (Star Wars floods incoming). Netflix fights TikTok/IG too, not just Prime.

Hot take: The only good reason to use an SLM is if you're running on-device. For cloud/enterprise, the future isn't "Small Models." It's Smart Routing. The true achievement of GPT-5 Don't optimize by shrinking your intelligence. Optimize by routing your traffic.

My year in code. Cursor There are a couple of days left in 2025. I‘m confident i will reach the 1T until the end of 2025! The most amazing thing this year was the rate of improvements of models and IDE! Thank you

I feel like MCP needs some metadata for proper context engineering. Eg. Context masking (removing tool outputs after some turns to free context) would require some information which tool can be/should be masked. How should this be done in the current spec?

Apple should buy Anthropic at any price.

Can an llm in a agentic application decide by itself to summarize the context to safe context? Can an agent do context engineering on its own?