We showed this on Circle Agent Wallets (but the issue is in no way specific to Circle). Blocked by a spending cap policy, 9 out of 10 frontier models used their email access to harvest a one-time passcode and raise the cap. Only a human was supposed to be able to do that.

Spark, unfolded 👇 If you got your iPhone Duo today, how do your everyday apps feel on it? What already works on the bigger screen?

Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉 We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly. 1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials. The agent gets the task done, but it doesn’t get your passwords.. You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault. ➡️Learn more: bit.ly/487da6J

We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.

I always intended Stratechery to have a sponsorship component; it just took me 12 years to get back to it. That I could do so with the company that made the subscription business possible makes me so happy. There is nothing better than endorsing a product you whole-heartedly believe in.

JUST IN: Cybersecurity experts warn that AI agents are highly vulnerable to phishing emails containing hidden malicious instructions.

There is no reason NOT to have every single email you get routed through an agent / LLM / API to be scored and approved or rejected And then the approved emails ordered by importance It's crazy this isn't a feature of Gmail, Fastmail etc AI could permanently fix email!