Sabitlenmiş Tweet
To deliver value at scale, Agents need to learn on the job.
jldec.me/blog/its-early…
English
Jürgen Leschner
2.4K posts
Jürgen Leschner
@jldec
Helping build a better Internet for agents and humans @cloudflare 🧡
Katılım Mayıs 2008
1.9K Takip Edilen389 Takipçiler
English
Spending my Sunday in a bunker at agentic.hamburg w/ @harshil1712
🟣 [DONE] Hold talk on DYI + Delegate with @fiberplane's fp to stay in touch with your codebase
🟣 [DONE] Visit @CloudflareDev AI Sandbox Workshop
Now some bumper car right at Dom Hamburg?
English
Jürgen Leschner retweetledi
woah pi basically "just works" in cloudflare workers runtime
English
... `git commit --amend --no-edit files` will do instant squash of changes in files using last message.
English
🔥🚀 How to scale to 1000s of agents (with memory) per human?
sunil pai@threepointone
full rewritten from scratch, now executed (and secured!) inside a dynamic worker, a lot lighter and powerful. much, MUCH more to come. (sharing here early because you know how we do)
English
Perhaps my favorite episode of latent.space so far
Latent.Space@latentspacepod
🆕 Claude Cowork, Skills, and the Future of AI Coworkers latent.space/p/felix-anthro… @felixrieseberg has spent years working at the interface layer, from Electron and the Slack desktop app to now helping build @claudeai Cowork. In this episode, Felix explains why execution is getting so cheap that teams can “build all the candidates,” why Anthropic is betting on local-first agent workflows, and why the future of AI products may belong less to chatbots and more to systems that can actually do knowledge work.
English
Jürgen Leschner retweetledi
Notion just got way faster! We now stream HTML from the edge → we're seeing the speed of a static site while keeping dynamic content
A @Cloudflare Worker starts streaming the <head> while fetching preload data, so by the time your browser boots Notion, the data's already there
Notion@NotionHQ
A li’l speed boost just shipped: Pages now load much faster. → P50 ~24% faster → P95 ~28% faster! Should feel snappier everywhere 🐊
English
Read this and then read it again. It's a glimpse into the future. sunilpai.dev/posts/after-wi…
English
@threepointone has a point.
"the important thing is the capability model."
sunilpai.dev/posts/after-wi…
English
very interesting
Evan You@youyuxi
Introducing Void, the Vite-native deployment platform: 🚀 Full-stack SDK ⚙️ Auto-provisioned infra (db, kv, storage, AI, crons, queues...) 🔒 End-to-end type safety 🧩 React/Vue/Svelte/Solid + Vite meta-frameworks 🌐 SSR, SSG, ISR, islands + Markdown 🤖 AI-native tooling ☁️ One-command deploys void.cloud
English
Jürgen Leschner retweetledi
Jürgen Leschner retweetledi
Building multi-agent systems? @NVIDIA's Nemotron 3 Super (120B A12B) is now on Workers AI.
- Reasoning and tool calling for complex multi-agent workflows
- Built for code, finance, cybersecurity, and search agent use cases
Learn more:
developers.cloudflare.com/changelog/post…
English
Jürgen Leschner retweetledi
Love this from Cloudflare.
/crawl is built around the norms that keep the web sustainable: identifying itself honestly in the user-agent string, respecting robots.txt and crawl-delay, honoring site preferences, and backing off when told to. 429s, retry-after headers, the works. And with maxAge-based caching, repeated fetches to the same URL hit a cached result instead of the origin again. Less waste, less unnecessary load on publishers.
Crawling is not scraping. Not even close.
The Internet is one of the most important heirlooms we have as a society. Billions of people contributed to building it: publishing, linking, sharing, cooperating across borders and institutions and decades. That does not happen again. You do not get to inherit something like that and strip it for parts. You do not get to automate around the preferences of the people who built it, ignore the norms that made it valuable, and call that innovation. That is extraction. It degrades something irreplaceable.
Scrapling and Crawlee are the wrong approach. People who reach for those tools when they should be crawling have made a choice. It is worth being clear about what that choice costs.
The voluntary shared agreement that made the web work depends on people actually honoring it. Publishers set preferences. Crawlers respect them. Everyone benefits. That only holds if enough people take it seriously.
Use the good tools (this one counts). Respect site preferences. Do your part.
Cloudflare Developers@CloudflareDev
Introducing the new /crawl endpoint - one API call and an entire site crawled. No scripts. No browser management. Just the content in HTML, Markdown, or JSON.
English
Can recommend 🧡
Eric Clemmons 🍊☁️@ericclemmons
Come work with me @CloudflareDev! job-boards.greenhouse.io/cloudflare/job… I'd like your help making Cloudflare Pages & Workers Builds (i.e. deploying on Cloudflare) simpler, faster, & more reliable 🙏 (Especially if you've used Cloudflare before!)
English
Jürgen Leschner retweetledi
📣 @cloudflare/codemode@0.2.0 release
Big change is new generateTypesFromJsonSchema to build types from OpenAPI spec or MCP list tools (how Cloudflare MCP Server works)
also no longer dependent on ai sdk. Specific functions (eg. createCodeTool) are imported from /ai
English
Jürgen Leschner retweetledi
Astro 6 is here! We completely rebuilt the Astro dev server and build pipeline onto a new, more powerful runtime-agnostic architecture.
Plus: New Fonts API, CSP support, an experimental new Rust compiler, and more...
astro.build/blog/astro-6/?…
English
Jürgen Leschner retweetledi
are you an ex-founder/cto in bay area that would like to help AI labs and SaaS leaders build on @CloudflareDev? looking for hands-on keyboard, grit and technical curiosity. dm me or send me a mail mdembo[at]cloudflare[.]com
English