During the next few days, I will share some of my private security research work that I have done in the last year. ​ All those projects are @aave related, and I feel very proud to have been chosen as one of the security partners to review them. I'm pretty sure that the dedication and knowledge that I have demonstrated on their codebase has been a pretty good investment 😁 ​ Those projects were very challenging, but at the same time it was fun and a pleasure because you always feel motivated and engaged when the quality of documentation, specifications and code is high quality. ​ When @avara or @bgdlabs contacts you, you know that you are going to enjoy it. They are both a top-notch team to work with. ​ The first one that I want to share is a.DI (Aave Delivery Infrastructure) It's a cross-chain communication abstraction layer for decentralised systems like the Aave DAO to communicate across networks, minimising the risk of underlying individual bridge provider failures, via consensus rules.

In your experience, even if you provide "guidance" via zod schema descriptions on "how to use" a tool and which are the input schemas/rules, how much is the model failing at calling the tool correctly? Is it "expected" that it fails and learns from the experience or should it always one shot it?

Can we get some Dots in the EU for the w/e?

MCP seems to be like Matter. It evolves with new versions, but no one (or at least the big ones like codex, opencode, pi and so on) does not adopt it. Aren't those actors in the MCP org?

dots demo. Now... with better WiFi.

From your experience, do you think that structured output and `strict=true` are still a need? Or are the models smart enough to not need it anymore when you are explicit in the expected output format in the prompt directly?

One thing that truly irritates me is that the codebase written by the coding agents is driven by what they want to implement in the tests (which are created exponentially).

I'm working on a complex product/service that has packages/apps and so on. I am at a point where I need to document both what the product/service does, how to use it and also have the technical part. This should be for both users/devs but also a way to share the product/service "context" with other AI coding agents that don't have my local memory/context. What's the best practice in this case?

Ready for a DevDay side quest? 10 builder challenges. 5 Codex Micros up for grabs. Complete any 5 side quests to earn 1 raffle ticket for each. 48 hours. Join from anywhere 🌎

It’s basically Jev with super powers within Luna?

Introducing dots, powered by GPT-6 Astra. Remarkably capable, always-on agents built to handle everything.

GPT-6.1 Sol release?

it seems that also the OpenAI team is at capacity even during the live demo at Dev Day? well at least we are on the same boat 😂

I like the idea of the @OpenAI DevDay event but I'm not sure if it makes sense to "pack" all the new products/features into a single event in the AI Era. This is something of the past which I think that also other big companies (like Apple for WWDC) should just drop and release those new features/products during the year. Maybe it makes sense as an event that show the long term plan of release during the year?

Get ready.

Do you have a skill that review the test suite and slim it down to what it's truly needed creating a rule that the AGENTS.md need to follow from now on? I feel like by default Codex keeps bloating the project with tests for any small change it is making.

What does it mean when GPT-6 Astra starts to go back and forth between two decisions? That both of them are valid and I need to evaluate them on my own? Not a very helpful coding assistant 😭

This morning I had this thought/realization: I think that in the future @Apple will be one of the leading AI Labs to release open weights model optimized for running on Apple devices.