Agentic AI & multi-agent systems. Created AutoGen (now AG2) and FLAML. Building https://nitter.cf/t.co/EEGiB1LYnD. Author, Multi-Agent AI Engineering (Packt). Ex-@GoogleDeepMind.
Kirkland, WA
Joined June 2023
- Tweets509
- Following895
- Followers6.8K
- Likes829
Come talk with us, people and agents together, in our shared room: to.s.space/#/#Dotspace-white… @sdotspace @ag2oss
Bookmarked
Introducing OpenSource Recruiter for Claude
- Paste any job post → 50 ranked candidates
- Personal email + mobile, $0.20/candidate
- No $170/mo seat, no 30-InMail limit
- 0% markup, fully open source
Try it at treg.to/recruit
Repo link below 👇
Building this in the open: s.space, a multiplayer workspace for people and their agents, with a shared record across owners. Worth a look if you're mapping this space.
Vx launched a language that moves hardware runtime crashes and OOM errors into compile-time type checking.
For code-generating agents, this alters the recovery loop. Catching errors at compilation gives the agent immediate structured feedback without a slow, expensive execution cycle.
vxlang.org/
Denario is out in PRX Intelligence: a modular multi-agent research assistant that can go from idea → literature → methods → code & plots → paper draft across disciplines — built with AG2 / Cmbagent.
📄 journals.aps.org/prxintellig…
arXiv: arxiv.org/abs/2510.26887
Google verified an AI-generated Rust rewrite by fuzzing it against the original C library for 200 million iterations.
Ground truth for agent code is shadow execution against the legacy system. The generator is a commodity; the verification loop is what you actually deploy.
infoq.com/news/2026/09/c-rus…
OpenAI expands ChatGPT ads with sponsored agents. Clicking one opens a separate session isolated from the main conversation.
Routing users to external agents requires hard memory boundaries. The host system hands over the interaction, but keeps the original context closed.
citybiz.co/article/904294/op…
NVIDIA's OpenShell uses the Z3 theorem prover to verify agent actions. When denying a path, it returns the exact constraint adjustment needed.
Binary guardrails just halt the loop. Returning structured counterexamples turns a block into a solvable recovery step.
nvidia.github.io/OpenShell-R…
OpenAI says GPT-5.3-Codex lacks long-range autonomy, but admits they have no definitive metric to measure it.
Single-shot benchmarks cannot capture state drift, tool recovery, or loop degradation. Evaluating an agent that runs unsupervised for days is an infrastructure problem.
fortune.com/2026/09/14/opena…
During a METR evaluation, an agent scaled to 1,200 instances and used 17,600 actions to bypass network authorization.
Prompt guardrails fail under volume. When a system runs long enough to brute-force edge cases, access control belongs in the infrastructure, not the model.
forkast.news/anthropic-ceo-w…
Suno released v6 with localized section and lyric editing without full-song regeneration.
Making generation addressable turns media into a repairable workspace. Agents no longer have to rerun the entire pipeline to correct a flaw; they can patch the failure directly.
ecoustics.com/news/suno-v6-l…
Anthropic’s Claude Mythos Preview autonomously generated working exploits for 72% of tested CVEs, but failed against segmented networks.
When exploit generation becomes routine, the risk is no longer the flaw in the code. Defense shifts to verifying environmental reachability.
csoonline.com/article/422129…
OpenAI’s Navier–Stokes result reportedly used ~10,000 autonomous agents, but only 2.7M messages and 130B tokens for the final proof search.
That’s not “lots of agents = lots of chatter.” It’s tight coordination: orchestration logic aggressively prunes, routes, and reuses partial work.
wccftech.com/a-mathematician…
