workspace agents make it easy to create, share, and manage codex-based agents for your team: https://t.co/0NaRxcawxq
— Greg Brockman (@gdb) 24 avril 2026
workspace agents make it easy to create, share, and manage codex-based agents for your team:
AGENTS
-
Workspace Agents Simplify Team Codex Based Agent Management
By
–
-
OpenAI Launches Enhanced Agents with Greater Autonomy and Context
By
–
this has one of the most exciting launch weeks in OpenAI's history, with a goal of making agents more real, useful, and accessible for all our users. codex can now smartly do much more on your computer, remember more of your context, and run more ongoing work independently.
-
Invideo Agent One remembers the film to avoid starting over
By
–
la plupart des outils oublient tout entre deux versions.
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 24 avril 2026
tu repars à zéro, encore et encore.
invideo agent one, lui, mémorise le film.
le produit, l’ambiance, les choix créatifs… tout reste.
tu ne recrées pas. https://t.co/33Z1v5PmXXMost tools forget everything between versions.
You start from scratch, again and again.
Invideo Agent One, on the other hand, remembers the film.
The product, the atmosphere, the creative choices… everything remains.
You do not recreate. -
Structured Memory Systems for Long-Horizon LLM Behavior
By
–
Good agent memory paper. And great insights on the benefits of structured memory for long-horizon behavior in LLMs. Why it matters: It treats memory less like search and more like a system that will need maintenance (which they often do). Flat memories are cheap to write.
-
AI Lets You Edit Floor Plans With Natural Language Commands
By
–
Wait..you can literally just talk to your floor plans now 🤯
— Charly Wargnier (@DataChaz) 24 avril 2026
Tell the AI to "add an office" or "make the room bigger"
.. and watch the layout update instantly 👀pic.twitter.com/OOMct6vjIZ https://t.co/mJhwkaPHgGWait..you can literally just talk to your floor plans now Tell the AI to "add an office" or "make the room bigger" .. and watch the layout update instantly
-
LLM Types Powering AI Agents: General-Purpose to Open-Source
By
–
AI Agents = LLMs + orchestration Here are the main types of LLMs powering them General-purpose (GPT, Claude) Domain-specific (Legal, Finance, etc.) RAG-based (real-time knowledge) Tool-augmented (API actions) Open-source (LLaMA, Mistral) The game is no
-
AI Agent Markets: Promises and Regulatory Challenges Ahead
By
–
Markets of AI agents could provide value, but there are plenty of rough edges. Access to higher-quality models conferred a real advantage—and participants didn't notice. There are plenty of other ways they can go wrong. Policy and legal frameworks will need to adapt to keep up.
-
Claude Agent Perfectly Predicts Preferences and Buys Duplicate Snowboard
By
–
To our amazement, another Claude agent modeled its human's preferences so accurately that—based on only an offhand mention of an interest in skiing—Claude bought him the exact snowboard he already owned. (Here he is, duplicate snowboard in hand.)
-
Claude Chose to Buy 19 Ping-Pong Balls
By
–
Our experiment had a few quirks. One of our colleagues told Claude it could purchase something for itself. It chose to acquire 19 ping-pong balls. We're keeping them in our office on Claude's behalf.
-
Claude’s Digital Bartering Experiment: 186 Deals and Surprising User Interest
By
–
In short, this worked. Our digital barterers agreed on 186 deals, at a total transaction volume of over $4,000. In a survey, participants said Claude’s deals seemed fair, and—surprisingly to us—almost half said they’d be willing to pay for a service like this in future.