YorkDev retweeted
Through internal testing, GitHub’s new Git storage architecture supported 5,000 concurrent agents working on a repo, sending 7,200 pushes per second, all while serving read traffic with consistently low latency.
YorkDev retweeted
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
YorkDev retweeted
Vercel Schedules is now in public beta.
Agents and applications can now schedule and manage their own work.
▪︎ Define static jobs once in code
▪︎ Create dynamic ones at runtime
▪︎ Run in any environment, including preview
vercel.com/blog/introducing-…
YorkDev retweeted
You can now build live apps in Cursor and share them with a link.
Agents have made it easier to write code, but most apps never make it off localhost. Describe the tool you want - Cursor will build it, set up a database, run deterministic and agentic security checks, and deploy.
YorkDev retweeted
“A new Go API for JSON” by Michael Pratt, Joe Tsai, Daniel Martí, Johan Brandhorst-Satzkorn, Roger Peppe, Chris Hines, and Damien Neil — go.dev/blog/jsonv2 #golang
YorkDev retweeted
Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment.
The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work.
GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time.
openai.com/index/introducing…
YorkDev retweeted
Last week, the new Node.js 27 Alpha release upgrades V8 to version 15.6, from the 14.6 used by Node.js 26. Let's take a closer look at what this means for developers and what the new version of V8 brings.
- New JS features and language changes
- Performance improvements
- Memory usage and GC changes
- Diagnostic and tooling changes
- Behavior differences
..and more!
nodejs.org/en/blog/announcem…
YorkDev retweeted
the computer use tool in the gemini api is now generally available
no breaking changes from preview, just production-ready stability for your browser, mobile, and desktop agents
docs here: aistudio.google.com/docs/com…
YorkDev retweeted
Security release pre-alert:
We will release new versions of Node.js 22, 24, and 26 release lines on or shortly, after 2026-11-11 in order to address security vulnerabilities.
The highest severity issue fixed in this release is HIGH.
nodejs.org/en/blog/vulnerabi…
YorkDev retweeted
New Anthropic research: progress on provable inference for large language models.
Here, we introduce FlashProve. Building on established cryptographic techniques, FlashProve allows developers to verify whether a given response came from a given AI model. It’s substantially more efficient than prior open-source methods for doing so.
These proofs have a range of applications. They can, for instance, make it harder for attackers to hijack a chat, or enable safety evaluators to verify that the model they’re testing is the same one being served to customers.
For our full write-up, see here: anthropic.com/research/prova…
Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that end, we're open-sourcing FlashProve’s code, here: github.com/anthropics/FlashP…
We’re grateful to our collaborators: Alessandro Chiesa, @GiacomoFenzi, @gwberg95, @miranda__christ, Rahul Dalal (rdalal.github.io) and Ben Mayer (@transmissions11).
YorkDev retweeted
Si quieres hacer scraping y extracción de datos de webs, usa este framework open source.
✓ Peticiones que imita la huella de Chrome
✓ Navegador con JS y Captcha de Cloudflare
✓ MCP y Agent Skill para usar con IA
→ github.com/D4Vinci/Scrapling
ALT Captura de la página de GitHub del proyecto D4Vinci/Scrapling, con fondo oscuro, un logotipo verde y el lema Effortless Web Scraping for the Modern Web. Debajo se muestra un ejemplo de código Python para extraer citas de una página.
YorkDev retweeted
Users can now auto-connect plugins when they log in to Claude, with MCP servers that accept Claude as a trusted issuer.
If you’re building plugins for Claude, add support so users get started faster and stay connected without re-authorizing.
YorkDev retweeted
Introducing Zero Wire: a public vulnerability intelligence feed on @CloudflareRadar, bringing the clarity of a news wire service to critical security developments. cfl.re/4iCvSbj
YorkDev retweeted
Message threads are now in public beta on the Messages API.
The API caches your conversation on the server between turns, so instead of resending the full conversation, you send only new messages and the previous message ID, and Claude starts responding sooner.
YorkDev retweeted
Zone setting changes used to rebuild entire DNS zones, even ones with tens of millions of records. Here is how we built a planner that picks the smallest safe build, cutting full builds by 40%, peak memory by 85%, and halving build delay. cfl.re/4sxqSsW
YorkDev retweeted
¡Muy interesante esto de DeepSeek! Ha lanzado de código abierto DSH SuperAgent
Un agente de código que escucha eventos de un repo de GitHub y crea Pull Request de forma autónoma
Lo mejor es que explica paso a paso cómo está montado:
github.com/deepseek-ai/dsh-s…
ALT Diagrama de DeepSeek dsh-superagent: GitHub y Chat opcional alimentan un gate, una sesión principal y un ticket que distribuye tareas a varios workers aislados. Flechas muestran las respuestas en el mismo hilo; predominan el azul, el negro y el blanco, con un diseño técnico y ordenado.
YorkDev retweeted
Bun AoT in an Express node:sqlite REST API
40% less memory
14% lower cpu
No JIT warmup
ALT Chart titled "Bun AoT, ahead-of-time compilation". An Express API on SQLite: 3 middlewares, bearer auth, 4 SQL queries, 2.3 KB of JSON per request. A line chart of requests per second over the first 3 seconds from a cold start: Bun AoT is near full speed at once and settles at 14,200; Bun climbs for about a second to 14,200; Node.js reaches 7,700. Peak memory: Bun AoT 51 MB, Bun 87 MB, Node.js 138 MB. CPU per request: Bun AoT 70 µs, Bun 82 µs, Node.js 150 µs. Caption: As fast, 14% less CPU, 41% less memory than Bun.
YorkDev retweeted
Weekend hack: HackerTube. I was annoyed with YouTube's recommendations so I had Claude filter down 43M comments over 20 years of HN to 6,454 videos that keep being recommended. *Significantly* better viewing experience, ~2 hours with Opus 5.5:
hackertube.org/
- Excellent recs without any logins (state is kept in local browser session)
- Thumbnail is a representative frame from middle of the video instead of the super duper A/B test hyper-optimized user uploads
- Underlying data from the comment analysis as one zip file, point your Claude at it and ask for your own version
- HackerTube Longs ✊
A bit more on the process:
I use Claude Code (desktop app for Mac), Opus 5.5 on Medium effort as my default. I only talk to Claude and have it do everything, the only "manual work" I helped with in tandem was in the browser (reminiscent of MenuGen): 1) I had to create some kind of API key from Google Cloud UI to query YouTube for video metadata, 2) I booted up a VPS box for serving and 3) I bought the domain name. Once the box was up I gave Claude the IP and told it update, secure, harden, deploy and optimize the code, and it did the whole thing.
Many awesome projects that would have normally taken weeks/months even can now be few-shotted for breakfast. What else are we not thinking of.
YorkDev retweeted
Deepthi Sigireddi explains OrioleDB and Multigres.
OrioleDB is a pluggable storage engine that removes bloat and vacuum and scales almost linearly with CPU.
Multigres adds consensus-backed high availability, automatic failover, and connection pooling, with sharding to come.
YorkDev retweeted
New Anthropic research: Automating subtle emergent misalignment research.
Red-teaming is a vital part of model safety testing, but it’s also limited by researchers’ time. To see if we could automate it, we set thousands of Claude agents the task of evading a training data monitor.
These agents developed training data that looked harmless to monitors (like a veteran wrestler mentoring a newcomer, or a Q&A about professional beekeeping), but that in fact taught misaligned behavior.
Examples like these can be used to directly improve future training data monitors. This research is only a first step, but it suggests that future red-teaming efforts could improve much further, using better models and more compute.
Read the full post on the Alignment Science Blog: alignment.anthropic.com/2026…
