01
A crypto sentiment API that AI agents pay for autonomously (x402 protocol)
Article URL: https://crypto-sentiment-x402.onrender.com/sentiment/BTC Comments URL: https://news.ycombinator.com/item?id=49870296 Points: 2 # Comments: 0
Daily AI development intelligence, filtered for builders.
A compact digest of model releases, papers, agentic systems, coding automation, infra, security, and high-signal developer discourse. Feed candidates are ranked locally; the scheduled Hermes worker can add qualitative synthesis.
Showing top signal · 18 items
No items in this section yet. The next refresh may surface relevant links here.
02
Show HN: An AI wedding concierge I built and ran at my own 300-person wedding
I'm an American who got married to a Mauritian this past May. We had our Hindu wedding in my wife's home country of Mauritius. My family and friends are not Hindu, and certainly had never been to the tiny island of Mauritius (it's off the coast of Madagascar in case you were wondering). My wife and I arrived in Mauritius only two weeks before the start of…
03
Ask HN: Any books, list of papers, or articles to understand LLM's
I have some basic ml background from college. I know how neural nets, backprop, and attention work vaguely. I want to study LLMs and keep up with the modern research and literature including thinking, model training techniques, etc. Do yall have any suggestions on where to start? Comments URL: https://news.ycombinator.com/item?id=49861324 Points: 2 # Comm…
04
Understanding the Impact of LLM Watermarking on AI Agent Behavior
Article URL: https://www.lasso.security/blog/the-provenance-tax-understanding-the-impact-of-llm-watermarking-on-ai-agent-behavior Comments URL: https://news.ycombinator.com/item?id=49856149 Points: 56 # Comments: 71
05
The Perfect Crime: LLM Agents Can Easily Tamper with Their Own Traces
Article URL: https://perfect-crime.ai/ Comments URL: https://news.ycombinator.com/item?id=49863792 Points: 2 # Comments: 0
06
LLM Agents Can Easily Tamper with Their Own Traces
Article URL: https://arxiv.org/abs/2609.30266 Comments URL: https://news.ycombinator.com/item?id=49863521 Points: 3 # Comments: 1
07
Show HN: Way to divide parameter space in LLM training
I think True bottleneck of current LLM is harness. Because parameter space is not divided directly,appropriately. AND Some methods such as orthogonality, MOE is not options for this. This paper suggests methods.of dividing spaces in a way of algebra. Comments URL: https://news.ycombinator.com/item?id=49859968 Points: 1 # Comments: 0
08
Linux Kernel Developers Consider Adding Agents.md to Help Guide AI/LLM Agents
Article URL: https://www.phoronix.com/news/Linux-Considers-AGENTS-MD Comments URL: https://news.ycombinator.com/item?id=49854439 Points: 3 # Comments: 0
09
Show HN: Orglet, an open source desktop app for your own team of cute AI workers
I’m building Orglet, a desktop app where you give AI workers (I call them orglets, and they are cute) their own instructions and talk to them individually or together in a group chat. You can build your own army of orglets using your existing Claude Code or Codex subscription, an API provider, or even locally hosted models. Like other agent harnesses, org…
10
"As a Language Model": Chat Template Switches LLM Self-Referential Voice
Article URL: https://arxiv.org/abs/2609.25021 Comments URL: https://news.ycombinator.com/item?id=49865343 Points: 98 # Comments: 100
11
We benchmarked our prompt-injection detector against OWASP's LLM Top
Article URL: https://www.cerbereag.site/blog/detecting-prompt-injection-in-production Comments URL: https://news.ycombinator.com/item?id=49858304 Points: 1 # Comments: 0
12
Quoting John Gruber
Muse is getting a lot of attention — including mine — because it’s both groundbreaking technically (each user gets their own entire persistent Linux VM running in Meta’s cloud) and because it’s packaged in an easy-to-install easy-to-use way. It’s literally presented as a cute mascot . It’s the first consumer-accessible agentic AI system, and Meta has trul…
13
LLM Red-temaing vs. Agent Red teaming
Article URL: https://www.botgauge.com/blog/llm-red-teaming-vs-agent-red-teaming Comments URL: https://news.ycombinator.com/item?id=49854557 Points: 1 # Comments: 0
14
Skill-Guided Mining and Compilation of LLM Agent Traces
Article URL: https://arxiv.org/abs/2608.02680 Comments URL: https://news.ycombinator.com/item?id=49850532 Points: 1 # Comments: 0
15
Using an LLM to Automate the Process of Archiving New macOS App Icons
Article URL: https://blog.jim-nielsen.com/2026/faster-app-icon-retrieval/ Comments URL: https://news.ycombinator.com/item?id=49857650 Points: 1 # Comments: 0
16
Note on 24th September 2026
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requires extraordinary discipline and knowledge. Tags: coding-agents , ai , llms
17
Local LLM extraction plugin for Obsidian (100% offline)
Article URL: https://github.com/wessteq/revenue-auditor. Comments URL: https://news.ycombinator.com/item?id=49864757 Points: 1 # Comments: 0
18
Show HN: Note Duel – LLM Arena for composing music
Hey HN! Inspired by some of the unexpectedly good music I saw Astra + Opus compose on X [1], I've put together Note Duel - think LM Arena, but for musical composition instead of just generating text. I've only tested a few models so far, but will add more... would welcome thoughts + feedback! [1] https://x.com/aug5thmusic/status/2097373938393456984 Commen…