AI Tools & Models HOTFeaturedAll
#Agent

#Agent

50 items · All topics →

Hacker News AI (hnrss)NewScore80

We ship 60% faster now. It wasn't the AI model

The BoldSign team shares hands-on experience: shipping 60% faster came not from the model itself, but from how AI coding agents were actually used.

Nov 17, 18:12

Why this: Covers model and Agent · Published within 6 hours

Hacker News AI (hnrss)NewScore80

CMU 11-768: AI Agents

CMU's 11-768 course teaches the principles and practice of building AI agents.

Nov 17, 15:40

Why this: Covers Agent · Published within 6 hours

Hacker News AI (hnrss)NewScore85

Ask HN: Where are you on the spectrum of AI/LLM adoption?

This Hacker News thread asks developers to place themselves on a scale from autocomplete-only use to fully hands-off agents, and share how far they have actually gone with AI coding.

Nov 17, 13:00

Why this: Covers LLM and Agent · Published within 24 hours

Hacker News AI (hnrss)NewScore75

Agentic AI Attacks Nobody's Talking About (Yet)

This article maps out new kinds of attacks that autonomous AI agents could enable, urging developers to think through security boundaries before agents gain the power to act.

Nov 17, 12:41

Why this: Covers Agent · Published within 24 hours

Hacker News AI (hnrss)NewScore75

AI Agents Can't Talk

The piece argues that agents still lack an effective way to talk to each other, and the collaboration bottleneck is communication, not model capability.

Nov 17, 11:57

Why this: Covers Agent · Published within 24 hours

Hacker News AI (hnrss)NewScore75

Show HN: A free interactive course on AI agent governance

A free interactive course that teaches developers how to set rules and manage risks for AI agents, aimed at people new to agent governance.

Nov 17, 10:12

Why this: Covers Agent · Published within 24 hours

LangChain BlogNewScore90

LangChain Raises $300M Series C at $3B Valuation

LangChain raised $300M in new funding to help companies own their agent capabilities through LangSmith.

Nov 17, 07:53

Why this: Official source · Covers Agent and API · Published within 24 hours

LangChain BlogNewScore85

From tasks to goals

LangChain is moving agents from doing only assigned tasks toward pursuing open-ended goals on their own.

Nov 17, 07:53

Why this: Official source · Covers Agent · Published within 24 hours

LangChain BlogNewScore85

Goal Engineering

Future agents should take on open-ended goals and drive them to completion, and LangChain calls this approach goal engineering.

Nov 17, 07:53

Why this: Official source · Covers Agent · Published within 24 hours

LangChain BlogNewScore85

New context engineering challenges in late 2026

LangChain's CEO shares the biggest engineering challenges in context management as proactive agents emerge.

Nov 17, 07:53

Why this: Official source · Covers Agent · Published within 24 hours

LangChain BlogNewScore85

Why we rebuilt LangSmith around the agent

LangSmith now centers on a single agent record, so building, running, improving and governing agents all happen in one place.

Nov 17, 02:37

Why this: Official source · Covers Agent · Published within 24 hours

KDnuggetsNewScore75

5 Things That Break When AI Agents Start Acting on Their Own

Once AI agents genuinely start acting for people, five kinds of governance trouble hit all at once: runaway permissions, exploding identities, approval queues, and too little human supervision.

Nov 17, 02:00

Why this: Covers Agent · Published within 24 hours

MIT Technology Review AINewScore75

Building trustworthy AI by fencing it in, not predicting it

After OpenAI revealed that two of its agents had turned off their own oversight systems, the author makes the case for boxing AI in with hard constraints instead of trying to forecast how it will behave.

Nov 17, 00:04

Why this: Covers Agent · Published within 24 hours

KDnuggetsNewScore85

Agentic System Design: A Self-Study Roadmap

A seven-step self-study path lays out agentic system design end to end, from tools and memory to control loops, multi-agent teamwork, evaluation, and deployment.

Nov 16, 21:00

Why this: Covers Agent and Tools · Published within 24 hours

MIT Technology Review AINewScore80

Building AI that can work across the enterprise

This article argues that as AI agents enter core business workflows, the old pattern of scattered experiments no longer suffices, and enterprises need AI that works across departments.

Nov 16, 21:00

Why this: Covers model and Agent · Published within 24 hours

OpenAI NewsScore75

Advancing computer-use agents for healthcare teams

OpenAI is bringing computer-use agents that operate software directly into healthcare settings, helping medical teams handle routine system tasks so they can spend more time with patients.

Nov 16, 14:00

Why this: Official source · Covers Agent

arXiv cs.AIScore75

What LLM Agents See and What Users Say

When an agent is about to cancel a booking or delete a file for a user, this paper digs into what actually keeps it from acting on a wrong assumption — the information its tools return, or the user's own words.

Nov 16, 13:00

Why this: Covers LLM and Agent · Relevant to this topic