FULL ARCHIVE
Follow the signal.
Browse every selected story by topic, beyond the twenty-item live edition.
AGENTS
59 STORIESAGENTS
Vercel and Shopify make agents first-class shoppers
Vercel Shop is now GA with agent-readable product pages and Shopify commerce tooling.
AGENTS
Crossing the Threshold: How OpenAI and Anthropic Approach Autonomy and Safety in Financial Agents
It distills fresh discussions from AI Engineer New York on agent autonomy and safety controls.
AGENTS
Putting Earth AI to work: Geospatial agents for our planet's biggest challenges
Google Research is presenting Earth AI as geospatial agents for major environmental challenges.
AGENTS
Amp puts AI agents to work beyond code with OpenAI models
OpenAI highlights Amp using new models and Sign in with ChatGPT for broader agent tasks.
AGENTS
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space published a new robotics interview centered on Dyna-2 and hour-long physical-agent autonomy.
AGENTS
Tokens Are the Cheap Part — Steve Jamison, Jellyfish
New conference talk highlighting cost structure lessons for production AI systems beyond token pricing.
AGENTS
The Agent Works. Does Anyone Trust It? — Michele Grant, Leading at Scale
AI Engineer published a talk on trust, reliability, and agent adoption at scale.
AGENTS
Are Harnesses Worth the Cost?
Martin Fowler published a comparative experiment on harnessed versus unharnessed coding-agent runs.
AGENTS
I Believe Everything My Agents Tell Me: Three Levels of Review — Corey Gallon, Rexmore
A recent YouTube talk lays out three review levels for agent-generated work.
AGENTS
How Anthropic’s Dynamic Workflows Coordinate Claude Agents
Anthropic outlined Unix-inspired patterns for coordinating Claude agents at AI Engineer New York.
AGENTS
Agents can now buy domains with the Vercel CLI
Vercel just announced agent-aware domain purchasing commands in its CLI.
AGENTS
Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab
Reliability remains a core blocker for deploying agents beyond demos and limited internal use.
AGENTS
Giving AI Agents Memory That Learns — Jake Broekhuizen, LangChain
LangChain shared a recent talk on agent memory systems that adapt from experience.
AGENTS
Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
Microsoft Research introduced Agent Lightning v1.0 for RL training of existing agents.
AGENTS
Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?
Latent Space profiles a new cloud-native agent harness effort from Kubernetes co-creators.
AGENTS
From 36% to 100%: How Self-Improving Agents Write Their Own Skills — Rafal Wilinski, Runlayer
Runlayer’s Rafal Wilinski presents self-improving agents with a claimed jump from 36% to 100%.
AGENTS
The Self-Improving OSS Agent Stack — Marc Klingen, Langfuse
Marc Klingen presented a talk on a self-improving open-source agent stack.
AGENTS
Codex Cloud shipped with Tailscale support. Nobody told us.
Tailscale says Codex Cloud support shipped, enabling private tailnet access with an auth key.
AGENTS
The Transcript Looked Fine. The Call Wasn't. — Debugging Voice Agents, Arize
Arize shared a practical voice-agent debugging talk focused on transcript-quality mismatches in live calls.
AGENTS
Your Coding Agent Is 6 Months Out of Date — Jakub Hojsan, Exa
New talk argues current coding-agent assumptions lag recent model and tooling changes by months.