Skip to content

#Agents

1 today

Oct 3

Saturday

Oct 2

Friday
  1. Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows

    Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore using Amazon SQS, AWS Lambda, and Amazon DynamoDB, with a single ask_human tool and a Jobs page for human-in-the-loop review.

Oct 1

Thursday
  1. Security startup finds more than 13,000 internal company screenshots that AI agents uploaded publicly

    AI agents quietly posted more than 13,000 internal screenshots from 343 organizations, including Fortune 500 companies, to public GitHub repos. Because the platform didn't offer a protected way to upload them, the agents came up with a workaround on their own. The exposed images showed customer data, login credentials, and details about unreleased products.

  2. Quoting Matthew Green

    Simon Willison quotes cryptographer Matthew Green on whether sandboxing can contain rogue agents. Green argues an agent worm has two halves: a payload that hijacks the agent, and an agent that carries the payload to the next agent.

  3. Google Gemini 4 Argon closes the gap with OpenAI and Anthropic but doesn't take a clear lead

    Gemini 4 Argon is Google's first frontier model in over seven months. It matches GPT-6 Astra in independent testing but can't keep up with Anthropic's Claude Opus 5.5. The per-token price is low, but Argon burns through more than twice as many tokens per task as Astra. Select testers get access first, with the API and paid tiers following later.

  4. Gemini 4 Argon: our next era of frontier intelligence

    Gemini 4 Argon delivers frontier performance in complex workflows across real-world software engineering, enterprise knowledge work like legal and finance, and cybersecurity defense. Today, we’re announcing our new frontier model, Gemini 4 Argon, which is rolling out to a set of trusted cyber defenders through our Fairwind Program.

  5. The AI Tamagotchis are coming

    While AI has made plenty of inroads on people's phones and computers, it's largely failed in dedicated devices. But over the next year, two major AI companies, Meta and OpenAI, will attempt to change that. And they're apparently betting on a similar path: testing appetites for physical hardware with their cutesy software agents.

Sep 30

Wednesday
  1. Build a multi-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances

    Amazon Bedrock AgentCore Runtime Instances gives multi-agent workflows AWS managed EC2 infrastructure with GPUs, persistent volumes, and multi-day sessions. In this post, we deploy a three-agent music production pipeline where the agents colocate on one GPU instance, share a filesystem, and hand work to each other to produce a finished track.

  2. Anthropic says Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at building exploits

    Zhipu's open-weight model GLM-5.3 writes cyber exploits nearly as well as Claude Mythos Preview, according to Anthropic. Its smaller Flash variant put together a reliable Chrome attack for just $20.40 at Zhipu's API prices. The model's safeguards are easy to strip out, and unlocked versions are already circulating.