Agent memory works best when it forgets the right things
Anthropic’s agent-memory research separates transcripts, notes, representations and injected context—and shows why selective consolidation matters more than storing everything.
Topic
Agents
<p>Autonomous systems, agent architecture, tools, memory and the new patterns of AI-assisted work.</p>
Hungary: Communist-era files released, up to 60k former agents revealed
Hungary released communist-era secret police files Wednesday, identifying up to 60,000 informants, a path for Hungary in reckoning with its repressive past. #EuropeNews
MCP Explained
Every MCP message on the wire, step by step. Transports, auth, tools, sampling, tasks, tool search and codemode. By Runlayer.
Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
Ricursive develop frontier AI methods to reinvent chip development, collapsing traditional design timelines, closing the loop between AI and the hardware that fuels…
Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hard
AI coding agent that makes a team of small models beat a frontier one - guregodevo/memdoor
AI isn’t replacing SREs, it’s deskilling them
When AI handles 95% of your incident response, do you get worse at handling the 5% that actually matters?
Cisco gives engineer unlimited AI tokens to rewrite legacy code
Meet Paddy, the 27-year-old Cisco’s president calls an “energizer bunny.” He’s been given unlimited AI tokens and told to “go nuts.”
AI, Lean, and the Future of Formal Verification, with Lean Creator Leo de Moura
Leo de Moura on Formal Proofs, AI Agents, and the End of “Trust Thedataexchange” Code. Subscribe: Apple • Spotify • … More
Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5
Google’s Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5, and second only to Claude Opus 5.5 on…
Claude Code regularly sends each background agent’s transcript to its model
Claude Code burns ~15-20% of your tokens on a 3-word status line: a Bun preload that turns agent_summary off · by Flamerix AI,…
Dayjob: Tax – evaluating AI agents on 50 professional tax assignments
DAYJOB: Tax evaluates AI agents across 50 realistic tax environments, testing their ability to navigate messy records, exercise professional judgement, and deliver reliable…
AI promised less work. Oioannou has never worked more
Agents made implementation cheap, so Oioannou started doing far more of it in parallel. Oioannou’s GitHub history since 2019 shows what that did:…