Visual builder for responses API. Chat kit and a probably underrated one – evals for non openai models. Difficult for evals startups, not just agent startups
TOOLS
-
Copilot Memory Update: Selective Forgetting Now Available
By
–
Underrated: AI that knows when to forget, not just remember. That's why we've updated Copilot memory to follow directions for both – and you can check + edit its memories any time under settings > manage memory. Live now in Windows, web + mobile. pic.twitter.com/ICqXzWhnaU
— Mustafa Suleyman (@mustafasuleyman) 6 octobre 2025Underrated: AI that knows when to forget, not just remember. That's why we've updated Copilot memory to follow directions for both – and you can check + edit its memories any time under settings > manage memory. Live now in Windows, web + mobile.
-

App Store Approval Process Coming Later This Year
By
–
Apps will have an app store like approval process, available later this year
-

ChatGPT App SDK Evolution: Canva Integration Inside ChatGPT
By
–
ok 2 years on, the new ChatGPT App SDK is much more fully fleshed out w integrations
— swyx 🐣 (@swyx) 6 octobre 2025
look at this ui. it’s not canva. it’s canva-inside-chatgpt.
this isn’t the chatgpt you grew up with. https://t.co/Ce8LlWVEbJ pic.twitter.com/BZloK1r6sMok 2 years on, the new ChatGPT App SDK is much more fully fleshed out w integrations look at this ui. it’s not canva. it’s canva-inside-chatgpt. this isn’t the chatgpt you grew up with.
-

ChatGPT Apps: First Strong AI Implementation with MCP Integration
By
–
Apps I chatgpt feels like the first good implementation of AI apps. I can see why they were dragging their feet on MCPs – apps sdk is built on them and this feels a lot better
-
OpenAI DevDay Live Blog Coverage and Announcements
By
–
Decided to live blog this morning's OpenAI DevDay announcements, since I'm in the audience
-

Petri Demonstrates Capabilities Testing 14 Frontier Models
By
–
As a pilot demonstration of Petri’s capabilities, we tested it with 14 frontier models across 111 diverse scenarios.
-

Anthropic Open-Sources AI Audit Tool for Claude Sonnet 4.5
By
–
Last week we released Claude Sonnet 4.5. As part of our alignment testing, we used a new tool to run automated audits for behaviors like sycophancy and deception. Now we’re open-sourcing the tool to run those audits.
-
Petri: Automated Agent Tool Audits AI Models Across Scenarios
By
–
It’s called Petri: Parallel Exploration Tool for Risky Interactions. It uses automated agents to audit models across diverse scenarios. Describe a scenario, and Petri handles the environment simulation, conversations, and analyses in minutes. Read more:
-
OpenAI Dev Day: Visual Agent Builder and Device Hints
By
–
OpenAI Dev Day keynote is at 10am Pacific. Looks like we’re getting a new visual agent builder, similar to what n8n, MindStudio, and Lindy are doing (but only with oAI models). Jony Ive is doing a fireside too. Maybe we get more hints at the oAI device too?
