At least some of the $6B investment should go into fixing this experience.

Great session about #MCP at #NYTechWeek hosted by Stainless and discussions afterwards. MCP has a lot of momentum, but it is new and everyone is doing it differently. I guess we will figure out the future of #AI and APIs in the future 🙃

Even in the age of AI-driven dev and agents, 'Anger-Driven development'— powered by incompetence and stupidity—still thrives.

That is how vibe coders will reinvent development best practices, separate environments and DevOps. In the end, you need to learn and understand things, some way or the hard way.

He managed to squeeze in his last concert just two weeks ago... R.I.P. 🦇 👑

Yeah, when asking it to break down implementation into steps - it always adds weeks of estimates.

This is how I feel about vibe coding. Any project I try that has any kind of complication has this immediate burst of progress. Things are amazing and it feels like a superpower. Then... as I add more complexity, things crash to a halt. The only projects that I think I can

I am once again begging you to put your database servers and application servers in the same region.

It's super fast and cheap, but for some reason it gives so many errors in Cline, retrying the same thing for many times.

None of it worked, but boy was it beautiful. 🤌🏼🤣

Compiled prompt 👇🏼 Generate a professional, high-resolution profile photo maintaining the exact facial structure, identity, and key features of the person in the input image. Frame the subject from the chest up with ample headroom and negative space above their head, ensuring

Interesting turn of events, they use Google to kill Google

Men, This is why understanding Debt is so Important ‼️‼️

DeepMind just did the unthinkable. They built an AI that doesn't need RAG and it has perfect memory of everything it's ever read. It's called Recursive Language Models, and it might mark the death of traditional context windows forever. Here's how it works (and why it matters

Disaster is coming. Thousands of ClawdBots are live right now on VPSs… with open ports to the internet… and zero authentication. This is going to get ugly. If your agent can: - browse the web - call tools - access files/secrets - hit internal endpoints …then an

Google just killed the document extraction industry. LangExtract: Open-source. Free. Better than $50K enterprise tools. What it does: → Extracts structured data from unstructured text → Maps EVERY entity to its exact source location → Handles 100+ page documents with high

🚨 Our #1 most requested feature is here: You can now export designs from any Stitch agent directly to Figma as editable layers. Vibe Design is perfect for exploring many ideas in minutes. But sometimes, you need that final layer of polish. Now you can move seamlessly between

welp, it was fun while it lasted folks

Because you wouldn’t let it slide… these are rolling out today for our most requested feature: Prompt-Based Revisions: Tweak, tailor, and tune your slides just by prompting the revisions you want PPTX Support: You can now export your Slide Decks (Google Slides coming next!)

17,000 tokens per second!! Read that again! LLM is hard-wired directly into silicon. no HBM, no liquid cooling, just raw specialized hardware. 10x faster and 20x cheaper than a B200. the "waiting for the LLM to think" era is dead. Code generates at the speed of human thought.