This is aside from the other key "software brain" problems of Codex and Code: dividing all work into front-end and back-end design, solving for the general case in a repeatable way, not testing or exploring idea spaces, testing for technical correctness but not other aspects…
TOOLS
-
Software-brained approach limits code tools for knowledge work
By
–
A fundamental problem with extending Codex/Cowork/Code to all knowledge work is that they remain very "software-brained" where the end result (the software) is what is important & that code serves as a source of truth. For a lot of other knowledge work, the process is at least
-
New Product Raven: Self-Evolving Agent OS
By
–
我又来剧透了
— 艾略特 (@elliotchen100) 21 juin 2026
从龙虾到爱玛氏，从爱玛氏到什么？
没错，我们马上要发布一个全新的产品：Raven。
它不是又一个「会调用很多工具」的 Agent。
它是一个会自我进化的 Agent OS。
大多数 Agent 的学习，停在技能层：多学一个工具，多记一条流程，多写一段 prompt。
Raven 不一样。… pic.twitter.com/KoO8KGMrPCHere I go again with a spoiler. From Lobster to Aimashi, from Aimashi to what? That's right, we are about to release a brand new product: Raven. It's not just another Agent that 'can call many tools'. It's a self-evolving Agent OS. Most Agents' learning stops at the skill level: learn one more tool, memorize one more process, write one more prompt. Raven is different.
-
Build your own Claude Code with Deep Agents
By
–
Great community article showing how to build a Claude Code-like agent using Deep Agents. Particularly relevant given how powerful GLM-5.2 appears to be! https://pub.towardsai.net/build-your-own-claude-code-using-langchin-a-deepdive-into-langchains-deep-agents-9ef98d98a69a …
-
Turn any paper into running code with autoarxiv
By
–
Turn any paper into running code.
— Akshay 🚀 (@akshay_pachaar) 21 juin 2026
Just swap arxiv → autoarxiv in the paper url.
That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies,… pic.twitter.com/UOPJnWdfLJTurn any paper into running code. Just swap arxiv → autoarxiv in the paper url. That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies,
-
Reference to GPT-5.6’s superiority in front-end
By
–
This is a reference to the fact that GPT-5.6 is significantly better in front-end, isn't it?
-
Meta AI unveils Artifacts tab to store presentations and documents
By
–
Meta AI gets a new Artifacts tab on the web. All presentations, documents, web pages and other creations would be stored there. Bridging the gap.
-
The bible for running LLMs locally now free online
By
–
DROP EVERYTHING The bible for running LLMs locally is now available online to read for free Covers what to use on – Laptop / edge / odd hardware
– Mac-first workflows
– Single RTX GPUs
– 2-4+ NVIDIA / CUDA GPUs
– General production serving
– Long-context / MoE / routing
– -
AI finds errors and updates grad school paper with new data
By
–
The interaction between AI & past scholarly work is going to get weird. Here I gave GPT-5.5 Pro a copy of my first published paper from grad school & asked it to find errors and update it. It found new data, analyzed it, created reproducible files, extended the key argument…