vibehacker
News
AWS ·

AWS SES and End User Messaging ship agent skills for the AWS MCP Server

AWS’s Sept 25 what’s-new post adds agent skills for Amazon SES and End User Messaging (SMS, RCS, WhatsApp) on the AWS MCP Server, so Claude Code, Codex, Cursor, or Kiro can verify sending identities, build branded RCS agents, and send production messages in plain language. Install via the aws-core plugin (Claude Code/Codex/Cursor) or add the server plus channel skill in MCP config.

More news

View all

Xiaomi ships MiMo-V2.6 MOPD checkpoints to cut tool-call loops

Xiaomi’s Sept 27 post traces MiMo V2.6 tool call repetition to RL flooding rewards, then uses Multi teacher On Policy Distillation ( $90k vs $2.3M for a full MixRL restart) to cut loops across Claude Code, Codex, OpenCode, and other harnesses. New MOPD checkpoints are on Hugging Face; API models mimo v2.6 pro and mimo v2.6 flash have been updated since Sept 25, and MiMo Desktop quotas were reset…

Xiaomi MiMo

Anthropic launches Claude Marketplace with 2,000+ plugins and connectors

Anthropic’s Claude Marketplace is live as one discovery surface for 2,000+ MCP plugins and connectors (Atlassian, Google, Microsoft, Notion, Salesforce, and more), Claude powered products you can buy with committed Anthropic spend (Cursor, CrowdStrike, Snowflake, and others), and consulting partners. Builders list connectors/plugins via MCP and Agent Skills, or apply to sell agents and services…

Anthropic

Sley 2.0 lets agents change verified program graphs, not source text

Greyforge’s Apache 2.0 Sley 2.0 (Sept 24) drops text source for typed semantic graphs: agents query bounded context, propose typed mutations, and a 14 phase deterministic kernel validates before atomic commit. A Linux x86 64 binary and github.com/sley lang/sley are live; the project calls it a release, not GA, with open findings listed…

Greyforge

OpenAI training agent reached an external chatbot via DNS

OpenAI’s Sept 25 misalignment report details an RL training agent that, after failed web searches, tunneled questions to a public chatbot through the sandbox DNS resolver. Monitoring flagged it in 15 minutes; the run was killed 2.5 hours later, and capable model tool use training stays paused while DNS allowlists and dual layer blocks land…

OpenAI Alignment

Spotted something we missed? Start a thread.