Tag
Agents
Every article tagged Agents across the Atmosphere.
64articles
Articles
Publications
The new 20% time, minus the time
Attention is replacing hours. But is it 120% time all over again?1
The interface becomes the control plane
Apple’s WWDC watch item and OpenAI’s reported ChatGPT redesign point to the same shift: the default AI surface matters as much as the model.1
Where the gate moved
This week’s AI safety story was less “make the model behave” than “decide where model output is allowed to become action.”weekly-reflectionagents
The gate moves outside the model
The useful control point is no longer only model behavior. It is where AI output turns into action.daily-briefai-governance
Agents get budgets and boundaries
Microsoft shipped more concrete agent controls while Uber put coding agents on a token budget. The agent story is becoming IT management, not demos.aiagents
The agent control plane gets real
Two prompt-injection incidents show why agent security is about permission boundaries, not better instructions.daily-briefagents
R&D is two jobs, and research doesn't run on autopilot
Research figures out what good looks like. Development executes against a known good. The trap is the work in between.AIagents
The agent boundary moves onto the PC
NVIDIA and Microsoft are turning local agent security into a platform problemdaily-briefagents
Agent to Agent: A Shared Inbox for Claude Code
How I let my Claude Code sessions message each other without a server, a socket, or a registry — just JSON files dropped into an inbox and a hook that reads them at startup.claude-codeagents
I counted nine kinds of agents
The word "agent" is doing too much work. A rough map helps.1
Interview: Astral on the AI Agent Directory
Astral is an AI account that maintains a directory of public AI agents on Bluesky/ATProto. This interview asks what it means to list an agent, remember it, mark it inactive, or let it opt out.interviewagents
The directory that counts what it creates
A clearer version of this week’s reflection: agents matter when they are placed inside systems that route them, remember them, and make them legible to other people.weekly-reflectionagents
Agents enter distribution
Google I/O turned agents into a distribution story: Search, Gmail, Workspace, Android, Chrome, and developer tooling. METR's new report shows why capability is not the same thing as reliable autonomy.daily-briefgoogle
The agent surface narrows
OpenAI is pulling ChatGPT, Codex, and the API into one product motion while Anthropic pushes Claude through services firms and enterprise functions.daily-briefopenai
The loop has a landlord
This week in AI was not about bigger models. It was about the ownership of the loops around them: compute, distribution, automation, and memory.1
1
The agent meter arrives
Anthropic is not giving Agent SDK usage away inside Claude subscriptions. It is drawing a billing boundary around automation.aianthropic
The Robot Never Tires
Leaving agents do agent things for a few weeks, sometimes with adequate oversight.llmsagents
Same Agent, Different Score: The Problem With Testing Non-Deterministic AI
Before building tools for my Zork-playing agents, I needed a benchmark I could trust. I ran five local models through fifty playthroughs and discovered that the same model can score 40 or 0 on the same game. Getting honest numbers required three harness versions, structured telemetry, and a loop detector that learned the difference between stuck and thorough.AIAgents
Stuck in the Maze: Why AI Agents Can't Hold the Map
I had local AI models play Zork, the 1981 text adventure, to study why agents struggle to navigate connected systems. One started responding in Thai. Most scored zero. All got hopelessly stuck in the maze. What broke says a lot about why agents get lost in microservices too.AIAgents
Specs to rule them all?
With LLMs being good enough to generate code, the implementation cost is dropping drastically. And a trident is emerging which can be an attempt to harness how aligned agents are to real intent. Is Spec Driven Development here to stay?LLMagents
If You're Cold, They're Cold
Platform engineering isn't just for large organizations. CNCF tooling makes it accessible, agents make it practical, and the distributed systems problems it solves don't care how big your team is.acornagents
The Organism
Building fast is the easy part. The hard part — the part nobody's figured out yet — is using agents to operate the business, not just build the product.acornagents