7 comments

  • TheTaytay 22 hours ago
    Do you support writing deterministic extractor scripts? I want to use an agent like this primarily as a way to help me write and refine deterministic extraction scripts, rather than involving the LLM for every iteration. If you don't yet, would you be up for talking about it? (And if so, should I email you or schedule an enterprise demo)?
    • antves 22 hours ago
      We don't support this yet, but we'd love to talk about it. Feel free to book a demo!
  • ayushr1 1 day ago
    Super impressive demo. Seems a lot faster than alternatives. How did you achieve that?
    • antves 1 day ago
      Thanks! It all boils down to (1) using small and efficient models, and (2) insisting on good context engineering. We describe the browser state in a way that's both compact and meaningful. This allows us to use tiny LLMs under the hood.
  • jasonriddle 22 hours ago
    Hi, thanks for sharing.

    My main concern with these browser agents are how are they handling prompt injection. This blog post on Perplexity's Comet browser comes to mind: https://brave.com/blog/comet-prompt-injection/.

    Also, today Anthropic announced Claude for Chrome (https://www.anthropic.com/news/claude-for-chrome) and from the discussion on that (https://news.ycombinator.com/item?id=45030760), folks quickly pointed out that the attack success rate was 11.2%, which still seems very high.

    How do you plan to handle prompt injection?

    • antves 22 hours ago
      This is a very valid concern. Here are some of our initial considerations:

      1. Security of these agentic system is a hard and important problem to solve. We're indexing heavily on it, but it's definitely still early days and there is still a lot to figure out.

      2. We have a critic LLM that assesses among other things whether the website content is leading a non-aligned initiative. This is still subject to the LLM intelligence, but it's a first step.

      3. Our agents run in isolated browser sessions and, as per all software engineering, each session should be granted minimum access. Nothing more than strictly needed.

      4. These attacks are starting to resemble social engineering attacks. There may be opportunities to shift some of the preventative approaches to the LLM world.

      Thanks for asking this, we should probably share a write-up on this subject!

      • creatonez 16 hours ago
        > 2. We have a critic LLM that assesses among other things whether the website content is leading a non-aligned initiative. This is still subject to the LLM intelligence, but it's a first step.

        > [...]

        > 4. These attacks are starting to resemble social engineering attacks. There may be opportunities to shift some of the preventative approaches to the LLM world.

        With current tech, if you get to the point where these mitigations are the last line of defense, you've entered the zone of security theater. These browser agents simply cannot be trusted. The best assumption you can make is they will do a mixture of random actions and evil actions. Everything downstream of it must be hardened to withstand both random & evil actions, and I really think marketing material should be honest about this reality.

        • antves 12 hours ago
          I agree, these mitigations alone can't be sufficient, but they are all necessary within a wider framework.

          The only way to make this kind of agents safe is to work on every layer. Part of it is teaching the underlying model to see the dangers, part of it is building stronger critics, and part of it is hardening the systems they connect to. These aren’t alternatives, we need all of them.

  • ukulerok 1 day ago
    I just wrote a complex prompt and it did a good job. How do you do evals or testing of your project?
    • antves 1 day ago
      Thanks for trying it out! We rely on a mix of internal benchmarks and academic benchmarks like WebVoyager.
  • PhilippGille 10 hours ago
    Is there a way to sign up without Google SSO?
    • antves 7 hours ago
      Not at the moment. Happy to run a task on your behalf if you'd like!
  • creatonez 20 hours ago
    So you're shamelessly selling spambots? The marketing here is wild... "proxy rotation"... "auto-CAPTCHA solvers"
  • JoshPurtell 15 hours ago
    Looks really good!