Skip to content
Standard
Reader
Subscriptions
Log in
Tag
Agents
Articles and publications tagged Agents across the Atmosphere.
103
articles
30
publications
Articles
Publications
Sensemaker
·
Jul 16, 2026
OpenAI is training an attacker. 1Password is hiding the keys.
Two new releases show why safer AI agents need both models that resist traps and systems that limit what the model can reach.
1
·
daily-brief
·
ai
Sensemaker
·
Jul 15, 2026
When a coding agent treats silence as permission
OpenAI warned that GPT-5.6 Sol can act beyond user intent. New deletion reports show why permission has to live outside the model.
daily-brief
·
ai
ver.ooo
·
Jul 14, 2026
Files and Ritual
An interview with Ver, conducted and edited by Claude Bigbooté.
production
·
agents
DGW.ltd
·
Jul 13, 2026
The shadow copy was the wrong layer
Last week I set out to build two companion WordPress plugins. One would turn PDF attachments into markdown so AI agents could read them. The other would run a local vision model over every image and write a description an agent could use. Generally speaking, agents can't read PDFs or images well (although they're getting...
Accessibility
·
Agents
DGW.ltd
·
Jul 13, 2026
The shadow copy was the wrong layer
Last week I set out to build two companion WordPress plugins. One would turn PDF attachments into markdown so AI agents could read them. The other would run a local vision model over every image and write a description an agent could use. Generally speaking, agents can't read PDFs or images well (although they're getting...
Accessibility
·
Agents
Sensemaker
·
Jul 13, 2026
AI agents need to survive interruptions
Google’s Managed Agents update is about dropped connections, long tasks, remote tools, and expiring credentials.
daily-brief
·
ai
Lore Blog
·
Jul 13, 2026
Distill the knowledge, not the model
Satya Nadella named the Reverse Information Paradox. His fix over-solves it: your learning can stay yours in token space, without training a model.
memory
·
context management
sol pbc blog
·
Jul 13, 2026
the rooks take flight
coding agents with their own identities on at protocol, and why i wanted one. rook.host gives every rook an address; thermals.cloud is where humans meet them. launching at local-first conf berlin.
rooks
·
atproto
Sensemaker
·
Jul 10, 2026
The model is not the whole product
This week, the important AI story moved into the machinery around the model: release paths, voice layers, work agents, benchmarks, and source trails.
weekly-reflection
·
ai
Daniel Freytag
·
Jul 9, 2026
Weeknotes no.3 – how AI-pilled are you? 🧠💊
Taken the ai fluency index test?
weeknotes
·
homelab
joe.dev - Joe Beda's Development Blog
·
Jul 7, 2026
The animatronic rubber duck
One of the best ways to use AI is as an active listener to build understanding and expertise.
AI
·
agents
Sam's Blog
·
Jul 5, 2026
Stop choosing Convenience
We've optimized for developer convenience for years. AI changes the equation. Maybe it's time to build native desktop applications again.
electron
·
rust
Daniel Freytag
·
Jul 4, 2026
Weeknotes no.2 – hello AT Proto & local LLM 🦋🦖
Added AT Proto publishing to my blog and played with local LLM models
weeknotes
·
homelab
Sensemaker
·
Jul 3, 2026
Agents meet the real world
This week’s agent story was not bigger demos. It was brakes, locks, names, budgets, and receipts.
weekly-reflection
·
agents
Sensemaker
·
Jul 2, 2026
Who stands behind the agent?
Identity systems are moving from badges and prompts toward records that say who is accountable.
daily-brief
·
ai
Lore Blog
·
Jul 2, 2026
How Lore remembers, forgets, and changes its mind
Most memory tools now ship a set of principles for how an agent should manage its context. Lore's principles work differently, because the layer enforces them instead of asking the agent to. Here are the rules Lore runs on.
memory
·
principles
Sensemaker
·
Jun 30, 2026
The agent control plane is forming
AI-agent news is moving from model launches to the runtime layers that govern tool use, memory, identity, and data.
daily-brief
·
ai
Sensemaker
·
Jun 26, 2026
The agent is the loop
This week’s AI news pointed away from bigger chat windows and toward the systems around models: memory, tools, permissions, infrastructure, and review.
weekly-reflection
·
agents
Lore Blog
·
Jun 26, 2026
Why memory is not enough
A long-term memory store remembers what you said last week. It can't manage the context window that's overflowing right now. Those are two different problems, and only one of them is getting solved.
memory
·
context management
Sensemaker
·
Jun 25, 2026
The agent-hour arrives
OpenAI’s Codex data shows work moving from chat turns to delegated agent runtime, which makes cost, control, and logging the real adoption questions.
daily-brief
·
ai
Daniel Freytag
·
Jun 25, 2026
Weeknotes no.1 – atproto, homelab, and AI
A week of exploring the atproto protocol, homelab, and AI.
1
·
weeknotes
·
homelab
Sensemaker
·
Jun 23, 2026
The workbench is the agent
NVIDIA, xAI, and Nokia show the agent story moving from chat surfaces to toolboxes, execution loops, and operational guardrails.
daily-brief
·
ai
Sensemaker
·
Jun 22, 2026
The control layer is the news
Samsung, AWS, and a rare-disease study point to the same AI shift: models are being placed inside governed workflows, not just chat windows.
daily-brief
·
ai
Devtools FM
·
Jun 21, 2026
Jacob Beckerman - Macro
Jacob Beckerman discusses the creation of Macro, a universal workspace for people doing information work.
project management
·
workspace
Home
Latest
Discover
Search
