Page 19 of 53 · 1,564 retained trends
A Hacker News discussion about Show HN: Beating GPT5.5-xhigh for Coding agent security with SLMs and IRM. The submitted context says: Coding agents craft arbitrary code so securing them is more complicated than red-teaming. We post trained a cyber-security small llm, changed how it reasons and supplemented our…
SpaceKit AI is a technology topic drawing discussion on Hacker News.
Unlimited AI calls, done sustainably is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about Will AI developers be on the bench of future Nuremberg-like trials?. The submitted context says: The Nazis basically said ‘i was just following orders’ - i.e. ‘chain of authority defense’. Will ai devs follow the same pattern of defense once/if an ai swarm does something…
AI Finds Critical Flaw in Bitcoin Lightning, Devs Issue Emergency Warning is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about Ask HN: Which class of business model is most resilient to build in the AI era?. The submitted context says: If you were to start a company today, what type of business model would you choose? Most new businesses have some form of AI in them, and this makes some sense during a gold rush,…
How to handle sensitive data in LLM agent workflows without breaking tool calls is a technology topic drawing discussion on Hacker News.
Terminal-Bench-Science: Evaluating AI agents on scientific research workflows is a technology topic drawing discussion on Hacker News.
Yet Another AI Builder But is a technology topic drawing discussion on Hacker News.
Awareness Local: local-first memory for AI coding agents (96% R5 on LongMemEval) is a technology topic drawing discussion on Hacker News.
The Dirty AI lie: How the GREATEST bet in human history started to crack [video] is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about A second model pays off in two shapes. The submitted context says: The claim is Anthropic's, from their cost-optimization guide: a second model paid off in two shapes, an advisor and an orchestrator. Nothing else they measured made the list.
Has Gemini AI has altered the interpretation of Google trends? is a technology topic drawing discussion on Hacker News.
AI-Powered Tilichu VST/AU Synth Released by Butterlamp Audio is a technology topic drawing discussion on Hacker News.
AI Lessons from Driving 200M Autonomous Miles is a technology topic drawing discussion on Hacker News.
Alphabet stock sheds $700B as AI bills climb is a technology topic drawing discussion on Hacker News.
Ask Me Twice – A longitudinal archive of AI chatbot responses is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about Show HN: ChessRabbit – The AI Chess Analysis Platform. The submitted context says: Hi HN! I wanted to share with you a chess analysis tool that I was building for the past week. First of all I want to explain what is the problem that I'm trying to solve: Chess…
Group size effects and collective misalignment in LLM multi-agent systems – PNAS is a technology topic drawing discussion on Hacker News.
Show HN: A focused workspace for creating short AI videos with H3 Max is a technology topic drawing discussion on Hacker News.
Please stop flooding our projects with AI slop to furnish your CV is a technology topic drawing discussion on Hacker News.
Show HN: Understudy: Scenario Testing for AI Agents is a technology topic drawing discussion on Hacker News.
MI: Measure Price Calculator – AI Pricing for Shopify is a technology topic drawing discussion on Hacker News.
In a divided America, left and right unite to oppose AI data centers is a technology topic drawing discussion on Hacker News.
A Turning Point in AI Writing is a technology topic drawing discussion on Hacker News.
sodiumsun/agenttrail is a GitHub project written primarily in HTML. Its repository describes it as: Local observability map for AI coding agents. Watch Claude Code, Codex, and Cursor plans, tool calls, file changes, and progress in real time.
Flare: Verifying MILP Reformulations with LLM-Based Theorem Proving is a technology topic drawing discussion on Hacker News.
AI's hacking capabilities are severely underestimated is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about Show HN: Collaborate with your team on Claude and ChatGPT artifacts. The submitted context says: We're been seeing an explosion of agent generated artifacts get shared in companies, but with no place to put them or comment on them their utility is limited. We're building Valet…
The AI 'Ghosts' Contaminating Academic Publishing is a technology topic drawing discussion on Hacker News.