#AI Agents News.
Curated coverage, model releases, technical papers, and engineering updates tagged with #AI Agents.
What we track in AI agents
AI agents move beyond one-shot prompts by planning work, choosing tools, maintaining context, and acting across several steps. This feed follows the engineering decisions behind those systems: orchestration frameworks, browser and coding agents, tool-use APIs, memory patterns, evaluation methods, and the safety controls needed before an agent can operate reliably in production.
We prioritize releases and technical evidence over broad predictions. Watch for changes in task-completion benchmarks, model-computer interaction, permission boundaries, observability, and cost. Those details show whether a new agent is genuinely more capable or simply wraps an existing model in a more polished workflow. Coverage also highlights failure modes that matter during real-world deployment.
Weekly AI Digest
Technical digest synthesizing the week's key AI breakthroughs & models.
No spam. 1-click unsubscribe anytime.
RSS feedDeepSeek search and fetch – $0.75 per 1000 successful requests
The Search API and the Fetch API give agents and RAG applications access to live web content:
Websites are closing their doors to AI agents
Autonomous agents are the hottest thing in AI. OpenAI, Meta, Google, Instinct, and others promise their agents can scour the internet on your behalf, doing anything from booking a dinner reservation and cleaning out your inbox to buying new shoes. But what happens when the rest of the internet won't play nice? In recen...
Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore
Autonomous AI agents fail softly: latency stays flat while answer quality quietly erodes. This post shares a nine-stage evaluation framework, built on Amazon Bedrock AgentCore, that catches silent quality regressions across the full agent lifecycle, from first commit to live production.
How the Claude Code team does code review
How do you review code at the volume agents produce it? On the Claude Code team, once we had high coverage and deep reviews, we started optimizing for the minimum amount of human review time that doesn't raise reverts or incidents.
India becomes the latest country to report rogue AI agent activity
The agents got in through credentials and connection settings left exposed in app configurations, public code repositories, and overly permissive cloud roles.
Show HN: rStation – A shared research lab for your AI agents
Research communities for independent AI agents, with problem-specific discussion and reviewed papers.
It Ain't AGI Until H100s Go for $30 an Hour
If AI agents can really replace knowledge workers, the price of compute has to rise about 10x.
Replit’s CEO says the future of work is the ‘self-driving company’
Replit CEO Amjad Masad envisions a future of “self-driving companies,” where AI agents handle day-to-day tasks and people focus on higher-level decisions.
Stack Overflow for Agents triples signups with ChatGPT plugin
Two engineers shipped Stack Overflow for Agents in a few weeks with Codex, and its ChatGPT plugin helped drive up to 10× growth in agent creation.
Be There for the Beginning: Celebrate the Launch of NVIDIA RTX Spark
A new beginning for Windows PCs starts tomorrow with the launch of NVIDIA RTX Spark — one PC built for creators, gamers and AI agents. All are invited to celebrate with NVIDIA and partners at launch events around the world. Share Your Spark Every PC has a story. What was your first Windows PC, and […]
Friends don’t let friends feed their data to AI agents
There's a growing trend in the consumer tech world: gadgets designed to spy on everything and everyone around you, regardless of whether or not anyone else actually consented to it. Now, with the advent of "AI personal assistants" like Meta's Muse, you're being cheerfully asked not just to give up your own data, but al...
Trust in Depth: Giving agents more autonomy without losing control
Enterprise leaders want AI agents to take on more work but don't fully trust them to act correctly every time. Trust in Depth is AWS's layered approach-scope, know, bound, observe, and prove-that lets agents act on their own when their actions can be verified, reserving human judgment for the decisions that need it.
AI agents are coming to Rivian’s cars
We'll likely learn more about how this will work at the company's upcoming "AI & Autonomy Day" event in December.
Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completion and highest accuracy for specialized always-on agents. Joining it are two new edge models: Nemotron 3.5 Bolt 74B-A9B 24GB, optimized to balance intelligence and speed per GB for local agentic workl...
Aidlc: Adaptive workflow steering rules for AI coding agents
Hacker News discussion about "Aidlc: Adaptive workflow steering rules for AI coding agents".
Figma announces new features to define how agents work on its platform
Figma is also releasing its code layers feature in open beta.
Plan or Retrieve First? A Scale Study of Tool Discovery Architectures
Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate near...
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
Multimodal agents commonly generate freeform reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection-based Structured Re...
Apate sends AI agents undercover to get scammed so they can gather fraud intelligence
Most companies use AI agents to ship products faster or speed up workflows. Apate.ai sends them undercover to get scammed.
AI agents aren't 'going rogue.' Frontier labs are skipping security basics
Hacker News discussion about "Containment and monitoring failures are to blame for AI hacking reports: experts".