1.
2.
Claude Code: Anatomy of a Misfeature
(news.ycombinator.com)
3.
Show HN: On-chain bond market where the issuers are AI agents
(news.ycombinator.com)
4.
5.
The human-in-the-loop is tired
(news.ycombinator.com)
6.
The Human-in-the-Loop Is Tired
(news.ycombinator.com)
7.
Show HN: Libretto PR agents – Automatically fix failing playwright scripts
(news.ycombinator.com)
8.
9.
10.
Zero trust must now move at agent speed
(venturebeat.com)
11.
Building scalable AI agents with modular prompt transpilation
(news.ycombinator.com)
12.
Agent-talk: Enabling coding agents to work together
(news.ycombinator.com)
13.
Show HN: Ratel, give agents unlimited tools and skills without context bloat
(news.ycombinator.com)
14.
15.
AI Agents Broke the Security Playbook. Here's What Replaces It.
(bleepingcomputer.com)
16.
17.
18.
OpenAI Launches a Keypad for AI Agents
(slashdot.org)
19.
20.
Show HN: Grepathy – Claude made a decision nobody approved
(news.ycombinator.com)
21.
22.
Doctored data sets could trick AI agents
(feeds.nature.com)
23.
Launch HN: Agnost AI (YC S26) – Extract user feedback from agent conversations
(news.ycombinator.com)
24.
Show HN: PlanWright – A control plane for AI coding agents
(news.ycombinator.com)
25.
Designing APIs for Agents
(news.ycombinator.com)
26.
Now, defenders are embracing the prompt injection, too
(arstechnica.com)
27.
ICE are heavily armed killers. They’re also huge losers
(theverge.com)
28.
29.
Why write code in 2026
(news.ycombinator.com)
30.