1441
Gemini 3.0 spotted in the wild through A/B testing
Testing Google's highly anticipated Gemini 3.0 through AI Studio's A/B feature using SVG generation as a quality proxy
New
The latest blog posts to take off on Hacker News. 6,220 posts.
1442
Claude Skills
Claude can now use Skills to improve how it performs specific tasks. Skills are folders that include instructions, scripts, and resources that Claude can load when needed. Claude will only access a skill when it's relevant to the task at hand.
1443
Codex Is Live in Zed
From the Zed Blog: OpenAI's Codex AI agent is now available in Zed via the Agent Client Protocol (ACP).
1444
Tor browser removing various Firefox AI features
Tor Browser 15.0a4 is now available from the Tor Browser download page and also from our distribution directory.
1445
Run interactive commands in Gemini CLI
We're excited to announce an enhancement to Gemini CLI that makes your workflow more powerful a...
1446
DoorDash and Waymo launch autonomous delivery service in Phoenix
Today, DoorDash announced a new partnership with Waymo to launch an autonomous delivery service in Metro Phoenix and introduce a limited-time $10 Waymo promotion for DashPass members in Los Angeles, San Francisco, and Phoenix.
1447
Why I Chose Elixir Phoenix over Rails, Laravel, and Next.js
Why I chose Phoenix LiveView over Rails, Laravel, and Next.js
1448
Lace: A New Kind of Cellular Automata Where Links Matter
This article is about a new kind of simple computational rule ("LACE rules" running on LACE, the Link Automata Computing Engine platform) which, when applied locally on a grid of cells, demonstrates fascinating emergent "artificial life" behavior.
1449
Electricity can heal wounds three times as fast (2023)
Chronic wounds are a major health problem for diabetic patients and the elderly – in extreme cases they can even lead to amputation. Using electric stimulation, researchers in a project at Chalmers University of Technology, Sweden, and the University of Freiburg, Germany, have developed a method that speeds up the…
1450
A stateful browser agent using self-healing DOM maps
Most browser agents forget what they’ve done. This one remembers, adapts, and learns, redefining how AI agents get work done.
1451
Where's the AI design Renaissance?
AI design is currently overhyped · Will AI take design jobs? · What should designers focus on in light of rapidly changing AI tools?
1452
Elixir 1.19
Elixir v1.19 released: type checking of protocols and anonymous functions, broader type inference, improved compile times, and more.
1453
When you get to be smart writing a macro
A story of writing Clojure’s println alternative that works inside threading-first/last macros
1454
New coding models and integrations
GLM-4.6 and Qwen3-coder-480B are available on Ollama’s cloud service with easy integrations to the tools you are familiar with. Qwen3-Coder-30B has been updated for faster, more reliable tool calling in Ollama’s new engine.
1455
1456
1457
Writing an LLM from scratch, part 22 – training our LLM
Finally, we train an LLM! The final part of Chapter 5 of Build an LLM (from Scratch) runs the model on real text, then loads OpenAI’s GPT-2 weights for comparison.
1458
ImapGoose
ImapGoose is a small program to keep local mailboxes in sync with an IMAP server. The wording “keep […] in sync” implies that it does so continuously, rather than a one-time sync. ImapGoose is designed as a daemon, monitoring both the IMAP server and the local filesystem, and immediately synchronising changes. When…
1459
Acrobat is intrusive, slow and non-customizable
Acrobat is intrusive, slow and non-customizable. Of course there are alternatives, specifically bad ones...
1460
Cheap DIY solar fence design
A year ago I installed a 4 kilowatt solar fence . I'm revisiting it this Sun Day , to share the design, now that I have prooved it out.
1461
A Gemma model helped discover a new potential cancer therapy pathway
We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models.
1462
Getting syntax highlighting wrong
Applying human ergonomics and design principles to syntax highlighting
1463
Things I've learned in my 7 years implementing AI
Even though the impacts of LLMs have never been seen before, they feel familiar to earlier assumptions.
1464
Recursive Language Models (RLMs)
We explore language models that recursively call themselves or other LLMs before providing a final answer. The aim is essentially unbounded context, and a way through context rot.
1465
US Passport Power Falls to Historic Low
For the first time since the Henley Passport Index was created 20 years ago, the United States is no longer ranked amongst the world’s Top 10 most powerful passports.
1466
Are hard drives getting better?
After 13 years, the data is clear—the bathtub curve does not apply to hard drives. And, more importantly, hard drives are failing less and lasting longer.
1467
Claude Haiku 4.5
Claude Haiku 4.5, our latest small model, is available today to all users.
1468
Zed is now available on Windows
From the Zed Blog: Zed for Windows is finally here. Download it today.
1469
Recreating the Canon Cat document interface
Exploring the emergence of user conventions in a minimal system.
1470
Exploring PostgreSQL 18's new UUIDv7 support
Exploring what's interesting about UUIDv7 support using a demo crab store.