←
StErMi10,541 posts
StErMi avatar

StErMi

@StErMi

#web3 dev + auditor | @SpearbitDAO LSR, @immunefi bug hunter, sage of AAVE codebase :D

◷ Joined April 2008▧ 307 Photos and videos
StErMi avatar
StErMi@StErMi·23 Jun 2024

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.

Post attachment
OpenAI avatar
⟳ StErMi retweeted
OpenAI@OpenAI·Nov 5

Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment. The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work. GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time. openai.com/index/introducing…

0:07
StErMi avatar
StErMi@StErMi·Oct 26

is there a reason why the default Codex behavior to "spawn" agents is with `fork_turns=all` that makes the subagents inherit the whole parent history inherited? Isn't the whole point of subagents to start with a "fresh" context? Am I missing something @OpenAI ?

StErMi avatar
StErMi@StErMi·Oct 25

I was thinking about the blog post "Building agents: When to fold subagents into your main agent loop" from @AnthropicAI this morning. I think that we have settled on the best practice (does it really exist one in this field?) that you have to structure your "agent workflow" depending on the context and the needs and the eval result. But being able to easily test it, evaluate it and maintain it has a cost and the same capability can't be easily embedded and provided as a tool, skill or subagent. I feel like we are at a point that we need a new standard that enables us to define capabilities and then "distribute them" to the agents that can consume them as skills or subagents depending on the context/need we have defined for that agent. claude.com/it/resources/arti…

StErMi avatar
StErMi@StErMi·Oct 21

Do I have any connection with someone from the Codex Cyber Program? When will you enable Daybreak Blue for GPT-6 Astra and GPT-6.1 Sol?

StErMi avatar
StErMi@StErMi·Oct 19

Codex has started to provide data illustrated as YAML instead of JSON during a discussion 🤔 It's the first time I've seen it.

StErMi avatar
StErMi@StErMi·Oct 19

Is it just me or the "suggested next prompt" feature in Codex macOS has stopped working across any chat? I've also tried to restart the app but it seems not to work anyway?

StErMi avatar
StErMi@StErMi·Oct 18

Here we go again... "Error running remote compact task: Selected model is at capacity. Please try a different model." @thsottiaux 😭

StErMi avatar
StErMi@StErMi·Oct 14

I'm 99% sure that they are releasing Dots in Europe but they have sent the email before enabling them on the Web. Well I assume that by the end of the day we will get Dots, so no reset for today @thsottiaux ? 😂

StErMi avatar
StErMi@StErMi·Oct 14

TIL that you can ask Codex to "create a new chat" to further discuss something and it will spawn a new chat. I don't know tbh the side effects or what happens under the hood. For example, in a chat where I had a long architecture discussion I've said "I agree with the overall architecture. Record it as agreed, then create a new chat to discuss and design P01, with the architecture, agreed rules, dependencies and relevant research as context." The original chat (which spawned the new chat) will in some way record it visually in the chat. Any guidance on the usage and which are the sideeffects or implications of adopting this behavior @Dimillian ?

StErMi avatar
StErMi@StErMi·Oct 11

I can't test OpenAI Dots because I live in europe but as far as I get you only get "one dot" for the whole account? How does it work internally? I mean it can't be a whole huge infinite context right? They "mask it" as a single conversation I assume (from the UI pov) but what happens under the hood?

StErMi avatar
StErMi@StErMi·Oct 10

How many of the big companies have finally capitulated to make a proper iPad app just to be ready for the iPhone Duo?

StErMi avatar
StErMi@StErMi·Oct 10

I've asked codex a UI/UX suggestion... it has linked a GOV UK guidance page 🤦 Now I understand why Codex is the WORST at design/UI/UX.

StErMi avatar
StErMi@StErMi·Oct 10

Now Codex suggests in the textbox the "following prompt" after that it has finished work. After implementing a request it has suggested "The filters should apply to all results, not just the current page. Implement server-side filtering through core, server, client and webapp." The question is: why hasn't it been done already during the implementation?

StErMi avatar
StErMi@StErMi·Oct 7

it seems that Codex thinks that I'm an organization/company? The error message is: "This content can’t be shown Daybreak isn’t available for <MY_APP_NAME>. Some cybersecurity requests may still be limited."

StErMi avatar
StErMi@StErMi·Oct 7

Again, and this time is within the Codex app. I'm part of the OpenAI Daybreak program and I still get these warnings. The "apply for Daybreak" brings me to an url that validates and verifies that I'm already part of the program... Do I know someone from the @OpenAI security team that can help me out here?

Post attachment

Do I know anyone from the @OpenAI Daybreak program or someone that can connect me with them? I'm part of the Daybreak program but my agents are failing. I'm using `gpt-6.1-sol` with my ChatGPT subscription. It appears that the error from the traces is "This content was flagged for possible cybersecurity risk. If this seems wrong, try rephrasing your request. Otherwise, confirm that the access_programs.cyber parameter is set to the appropriate tier, and note that some cybersecurity requests are still limited, even when Daybreak is on."?