Building https://xitter.cf/t.co/MnbBMAU6jU - Catch Up on Podcasts, 10x Faster.
EU 🇪🇺
Joined April 2009
- Tweets550
- Following427
- Followers119
- Likes677
Andrei Matei retweeted
US: Tesla Roadster. EU: tethered bottle caps.
I made that joke too. But let me be serious for a moment.
Made in Europe.
Europe built it.
Others told the story.
The Web was born at CERN.
Linux in Helsinki.
Python in Amsterdam.
ARM, the chip in your phone and your Mac, in Cambridge.
DeepMind in London.
The first commercial microprocessor was designed by an Italian, Federico Faggin.
Every leading-edge chip on Earth is printed with ASML machines from the Netherlands.
Mistral trains frontier open models in Paris.
Hugging Face: French founders, although it is headquartered in New York.
llama.cpp, the engine of local AI, started in Bulgaria.
The first mRNA vaccine came from Mainz.
Europe doesn’t lack innovation.
It lacks a megaphone. 🤷🏻♂️
Innovation without narrative becomes someone else’s success.
This isn’t Europe vs. anyone.
I love innovation wherever it happens.
I just want Europeans to feel proud and optimistic about the future again.
Did I miss something relevant here?
Claude is going the other direction, but honestly I kind of like this. It's very clean. On the other hand I would still prefer @plannotator :)
Antigravity 2.0 now features a dedicated planning mode, just like the Antigravity CLI.
Type /plan and the agent steps back to think through the task, and conduct extensive research, before generating an implementation plan for your review. The agent will ask for your approval before it begins executing on the task.
You can also ask for a plan naturally in your prompt, for a lighter version of a plan.
Anyone on #wsocial? Thoughts?
100%dead as bluesky
0%has chances
2 votes • Final results
Each time i’m prototyping something new I’m getting AI fatigue. Setup MCPs, setup allowed tools, bla bla bla. This services dove part of the problem.
It’s worth trying at least
Tool Gateway is now live in Nous Portal.
No separate accounts, no API key juggling. All you need is one subscription, and everything works.
A paid Nous Portal subscription now includes access to 300+ models and a growing set of third-party tools.
Launching with:
→ Web scraping
→ Browser automation
→ Image generation
→ Cloud terminal backend
→ Text-to-speech
Oh wow 🍿
This Shouldn’t Be Able to Run 120B Locally youtu.be/RkzCAaIV_cQ?si=ASVY… via @YouTube
AI has become a massive part of how we build software, and as an Engineering Manager, I'm genuinely excited by the real impact it's having on team velocity and output.
I'm lucky to work at an AI-first company where we get to experiment hands-on with the latest tools and trends every week.
Lately, I've been thinking about the question of adopting standards like OpenSpec for spec-driven development with AI coding agents.
My honest take: it's a tempting idea on paper — structured specs, better alignment between human and AI — but in practice, I've found it often adds overhead and ends up slowing us down more than it helps.
On the flip side, @plannotator has been an absolute game-changer. It supercharges Claude's plan mode by letting you visually review, annotate, and iterate on plans before execution. We've seen roughly 10x better leverage out of plan mode since adopting it.
If you're running an AI-powered SDLC (especially with Claude Code or similar agents), I can't recommend Plannotator enough. It turns "plan mode" from a nice-to-have into something truly powerful.
What are your go-to tools for keeping AI agents aligned without killing momentum? Curious to hear what's working (or not) for your teams! 👇
Wait what?
We've reached an agreement to acquire Astral.
After we close, OpenAI plans for @astral_sh to join our Codex team, with a continued focus on building great tools and advancing the shared mission of making developers more productive.
openai.com/index/openai-to-a…
Once upon a time, people waited hours in line for the newest iPhone. Now they have Claude caves praising a tool that promises financial independence.
Imagine AGI and fighting for the right to marry your favourite model … LLM that is.
I was using handy.computer, but having it ootb seems way better 🚀🚀🚀🚀
More and more companies are realizing the real value of AI — and that's speed. There is absolutely no excuse to keep reviewing line by line, comment by comment.
The future is today.
Over 1,300 Stripe pull requests merged each week are completely minion-produced, human-reviewed, but contain no human-written code (up from 1,000 last week).
How we built minions: stripe.dev/blog/minions-stri….
A sneak peek of something coming to Skimr.app very soon. AI is everywhere and phones are more capable than ever, so why not transcribe and extract notes directly on your device?
Monday morning. 9,000 CLOSE_WAIT connections and climbing.
I open Claude Code.
It analyzes the codebase, builds a plan, identifies the root cause. Confident diagnosis: no connection pooling. The fix: add a shared requests.Session() with a proper HTTPAdapter. Classic solution. Case closed.
Except the leak got worse.
Here's what neither of us caught at first: connection pools only help when you're hitting the same hosts repeatedly. Our worker was making 10,000+ requests — one to each unique podcast RSS feed. A different host every single time.
So the pool just accumulated open sockets to hosts that would never be contacted again. Cloudflare closes idle connections after ~90s. The remote side moves on. Our side enters CLOSE_WAIT — and stays there forever, because the pool never evicts a connection it never needs to
reuse.
The actual fix was the opposite of pooling: a per-call session that calls session.close() in a finally block. Explicit close. Every time. No accumulation.
9,000 → 58.
The lesson: Claude Code is a great thinking partner — but "connection pool" is such a well-known best practice that we both reached for it instinctively. The real work was questioning whether the pattern fit the problem.
It didn't.
So Anthropic is offering "$50 free extra usage". Nice, let's activate extra usage and see how it goes.
Plan plan execute, test, make some changes, test again.. 20$ are gone. Wow, clearly Ultra is much more value :)