Viewing profile — eric-burel

Infrastructure provisioning is a key ingredient of agentic AI viruses: https://www.ericburel.tech/blog/ai-virus-agent This may be the first steps of the worst wave of spamming camp…

They love their dictator until it backfires, that's a quite old story.

I've been working on making the "lethal trifecta" concept more popular in France. We should dedicate a statue to Simon Wilinson: this security vulnerability is kinda obvious if you…

Can it be used to sandbox an AI agent, like replacing eg Cursor or Openclaw sandboxing system?

The thing is running it onto your machine is kinda the point. These agents are meant to operate at the same level - and perhaps replace - your mail agent and file navigator. So if …

Before using make sure you read this entirely and understand it: https://docs.openclaw.ai/gateway/security Most important sentence: "Note: sandboxing is opt-in. If sandbox mode is …

Related: https://news.ycombinator.com/item?id=46223311 Switching to paid version was already problematic as it uses GCP account system which doesn't have a spending limit, and API …

Microsoft is using the deep penetration of SharePoint in companies to sell Copilot license. At least in France it's well and alive and I see much more Copilot licenses than actual …

Yeah I mean you can replace sandboxing buy other safe alternatives but the idea is the same, the generated code has to be considered as 100% untrusted. Supply chain attacks are esp…

Talking about the debt of a system prompt feels really weird. A system prompt tied to an LLM is the equivalent of crafting a new model in the pre-LLM era. You measure their success…

In an agentic setup you are still dependent on having relatively smart models that's true.

You can have an agent that focuses on studying the interactions. What you're saying is that an AI cannot find every security issue but neither do humans otherwise we wouldn't have …

Sounds a lot like "nationalism in a single country"

You may want to read about agentic AI, you can for instance call an LLM multiple times with different security consideration everytime.

Smart, thanks for the tip

AI is good for discovery but not validation, I wanted experienced human feedback here

"You can investigate this yourself by putting a logging proxy between the claude code CLI and the Anthropic API using ANTHROPIC_BASE_URL" I'd be eager to read a tutorial about that…

I call that self-destructive prompting in the sense that you use AI to output programs that replace calling the AI in the future. The paper seems to indicate that this also brings …

I am pretty sure you can figure massive loopholes like how it's legal to train the model on stolen data but not to steal data etc. For instance advertisers can push model benchmark…

"that could redefine the web economy" I don't think that ads in ChatGPT are that disruptive, it's just another channel. I think ChatGPT apps are an order magnitude more game changi…