Harness engineering finally got its 100-page academic survey paper from UIUC, Meta, and Stanford. Claude Code, Codex, and SWE-agent share the same 3-layer architecture under the hood: Interface · Mechanisms · Scaling Which layer is yours missing?
LLMS
-
Gemini 3.5 Flash Tops APEX-Agents-AA Benchmark
By
–
Gemini 3.5 Flash ranks first on the APEX-Agents-AA benchmark, outperforming significantly larger models.
-
Qwen 3.7 Max achieves 10x speedup in autonomous 35-hour run
By
–
Alibaba released Qwen 3.7 max. Benchmarks incredible. Their new model ran autonomously for 35 hours, made 1,158 tool calls, and achieved a 10x speedup – on a single attention kernel. This isn't "AI improving itself across the board." It's a model grinding through
-
Managed Harness for AI Agents: Deepagents, Model-Agnostic, One-Line Deploy
By
–
A managed harness: Built on the `deepagents` harness Durable execution out of the box Model-agnostic One-line deploy- no Dockerfile, no infra glue
-
Managed Deep Agents Private Beta Launched for AI Infrastructure
By
–
Managed Deep Agents is now in Private Beta ICYMI: It’s managed, model-agnostic infra for deep agents you can deploy with a single line of code. A quick thread on what you get out of the box
-
Paper: Conversational Interfaces as a New Biology Interface
By
–
The next interface to biology may not be a dashboard.
It may be a conversation. I just read a new preprint by Yanbo Zhang and Michael Levin that feels like it belongs in the “this may open an entirely new category” folder. The paper is called: “Language Game: Talking to -
Fields Medal awarded to OpenAI GPT5.5
By
–
Fields Medal for @OpenAI GPT5.5 🔜 https://t.co/f0sMD9nNEv
— Nando de Freitas (@NandoDF) 21 mai 2026Fields Medal for @OpenAI GPT5.5
-
Alibaba Qwen 3.7 Max Agentic Coding Model Benchmarks
By
–
Alibaba released Qwen 3.7 Max, its latest proprietary model for agentic coding. Qwen 3.7 Max scores 56.6 on the Artificial Analysis Intelligence Index, outperforming recently released Gemini 3.5 Flash and Kimi K2.6.
-
Top AI Stories: OpenAI Math Breakthrough, Google Co-Scientist, Tools
By
–
Top stories in AI today: – OpenAI cracks an 80-year math belief
– Google's AI Co-Scientist heads to labs
– Audit Claude’s context of you and your work
– Emergence’s five-town AI alignment showdown
– 4 new AI tools, community workflows, and more -
Cohere Command A+: Parallel Block Architecture Innovation
By
–
You're paying for closed models when Cohere just dropped this for free.
— AlphaSignal AI (@AlphaSignalAI) 21 mai 2026
And the real story in Command A+ isn't the benchmarks.
It's the parallel block design.
Standard transformers run attention and feedforward layers sequentially. This model runs them side by side, same… https://t.co/PEMZNEzAN9You're paying for closed models when Cohere just dropped this for free. And the real story in Command A+ isn't the benchmarks. It's the parallel block design. Standard transformers run attention and feedforward layers sequentially. This model runs them side by side, same