361.
362.
Show HN: An A2A-compatible, open-source framework for multi-agent networks
(news.ycombinator.com)
363.
LLMs are bullshitters. But that doesn't mean they're not useful
(news.ycombinator.com)
364.
365.
366.
367.
When UPS charged me a $684 tariff on $355 of vintage computer parts
(news.ycombinator.com)
368.
Show HN: Continuous Claude – run Claude Code in a loop
(news.ycombinator.com)
369.
Create a Lifetime of AI Voice, Video, and Images in One Platform for $90
(feeds.feedburner.com)
371.
Drawing Text Isn't Simple: Benchmarking Console vs. Graphical Rendering
(news.ycombinator.com)
372.
The write last, read first rule
(news.ycombinator.com)
373.
The Write Last, Read First Rule
(news.ycombinator.com)
374.
Linux in a Pixel Shader – A RISC-V Emulator for VRChat
(news.ycombinator.com)
375.
Context engineering can save your company from AI vibe code overload
(news.ycombinator.com)
376.
377.
You should write an agent
(news.ycombinator.com)
378.
You Should Write An Agent
(news.ycombinator.com)
379.
The Parallel Search API
(news.ycombinator.com)
380.
381.
382.
From vibe coding to context engineering: 2025 in software development
(technologyreview.com)
383.
Patching 68K Software – SimpleText
(news.ycombinator.com)
384.
385.
The Pixel 10 Pro’s new voice typing is wild, and it’s changed how I use my phone
(androidauthority.com)
386.
Kimi Linear: An Expressive, Efficient Attention Architecture
(news.ycombinator.com)
387.
Show HN: Pipelex – Declarative language for repeatable AI workflows
(news.ycombinator.com)
388.
Glyph: Scaling Context Windows via Visual-Text Compression
(news.ycombinator.com)
389.
390.
DeepSeek may have found a new way to improve AI’s ability to remember
(technologyreview.com)
Today's top topics:
ultrasonic espresso