This week's edition of my email newsletter features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new chapter of my Agentic Engineering Patterns guide https://
simonw.substack.com/p/gpt-55-chatg
pt-images-20-qwen36-27b
…
AGENTS
-
Newsletter Covers GPT-4.5, ChatGPT Images, Qwen3 and Agentic Patterns
By
–
-
Autonomous Multi-Agent System Coordination Challenge
By
–
If you figure out how a large multi-agent system can autonomously coordinate to maximum effect, you’ll win a Nobel Prize, a Turing Award and a trillion-dollar fortune all in one.
-
OpenAI and NVIDIA Partner to Roll Out Codex and GPT-5.5 at Scale
By
–
Amazing to see @nvidia go all-in on Codex! We’ve started going deep with a few companies to roll out Codex and GPT-5.5. Seeing it work this quickly at this scale is exciting. Let’s fire up those Blackwells!
-
GPT-5.5 Marks Shift from AI Tools to Autonomous Operators
By
–
GPT-5.5 signals a shift from “AI tools” to true autonomous operators.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 24 avril 2026
The question now isn’t what can AI do?
It’s what are you ready to hand off? https://t.co/1fP2bUCHvDGPT-5.5 signals a shift from “AI tools” to true autonomous operators. The question now isn’t what can AI do?
It’s what are you ready to hand off? -
8 Types of LLMs used in AI Agents by @ingliguori
By
–
8 Types of #LLMs used in #AIAgents by @ingliguori #GenerativeAI #ArtificialIntelligence #MachineLearning #MI
-
Guardian Agent Auto-Review Safety Evaluation in Codex
By
–
auto-review now live in codex — using a guardian agent to evaluate the safety of proposed actions, reducing human approvals to only when they're really needed. https://t.co/B1IhkqBZaL
— Greg Brockman (@gdb) 24 avril 2026auto-review now live in codex — using a guardian agent to evaluate the safety of proposed actions, reducing human approvals to only when they're really needed.
-
Sakana AI Fugu Launches Beta API with Recursive Test-Time Scaling
By
–
One of my favorite things about Sakana Fugu is the recursive test-time scaling. When allowed to call itself recursively, it reads its own prior output and spins up corrective workflows on the fly. We are opening up the API for beta testers to try it out: https://
sakana.ai/fugu-beta/ -
Sakana Fugu Beta Launches Multi-Model Orchestration Platform
By
–
We’ve been using Sakana Fugu internally for our own research and coding. Instead of relying on a single model, it dynamically orchestrates the best combination of open and closed models for any task. The future of AI is collective intelligence. Excited to open the beta release:
-
Sakana Launches Fugu: Multi-Agent AI Orchestration System Beta
By
–
We’re launching the beta for our new commercial AI product: Sakana Fugu , a multi-agent orchestration system! Blog: https://
sakana.ai/fugu-beta Fugu hits SOTA on SWE-Pro, GPQA-D, and ALE-Bench, and has been our internal secret weapon. It dynamically coordinates frontier models, -
Managing CPU and RAM consumption from AI agents
By
–
My main use for the terminal is to work out what the hell is killing my CPU/ram. It is typically some playwright, heavy chrome tabs, could be computer use and some other random stuff. Agents are not very good in tidying up after themselves.