Viewing profile — anerli

In my experience it's actually very doable to do reliable tool calling with a generic response format across models. You just need to disable native tool calling completely and pro…

yup, we've been using this approach with our product to make composing different integrations easier for the LLM and also give it the flexibility of code. Main difference is we use…

Hey HN - Anders and Tom here. We made a browser MCP using the same vision-first scaffolding as our SOTA (94% WebVoyager) browser agent Magnitude. This approach is more flexible and…

Hey HN, Anders and Tom from Magnitude (YC S25) here. On our last Show HN post about our open-source browser agent, someone left a comment - "there are multiple similar projects lik…

So there’s a very big difference in the sort of vision approach that browser-use does vs. what we do browser-use is still strongly coupled to the DOM for interaction because of the…

^ syncthing is nice

We do believe in a hybrid approach where a fast/deterministic representation is saved - but think there is a more seamless way were the framework itself is high level and manages t…

Hey, curious about your use cases for a chrome extension, care to share more? To answer your question - BAML is as DSL that helps to define prompts, organize context, and to get be…

Only one that's worth using ;)

I think the difficulty with this approach is (1) you want a good "lookup" mechanism - given a task, how do you know what cache should be loaded? you can do a simple string lookup b…

Yeah, I think its a little tricky to do this well + automatically but is essentially our goal - not necessarily literally writing a script but storing the actions taken by the LLM …

For context, we have no affiliation with KeysToHeaven (though we appreciate his comment). We do think our vision-first approach gives us a significant edge over other browser agent…

Both of them are "visually grounded" - meaning if you ask for the location of something in an image - they can output the exact x/y pixel coordinates! Not many models can do this, …

Yeah we've though about this approach a lot - but the problem is if your final program is a brittle script, you're gonna need a way to fix it again often - and then you're still de…

Glad you were able to get it set up quickly! We currently are optimizing for reliability and quality, which is why we suggest Claude - but it can get expensive in some cases. Using…

I think depends a lot on how much you value your own time, since its quite time consuming to write and update playwright scripts. It's gonna save you developer hours to write autom…

Try it out and report back!

Exactly :)

Hey! To have a framework that can effectively control browser agents, you need systems to interact with the browser, but also pass relevant content from the page to the LLM. Our fr…

Hey HN, Anders and Tom here. We had a post about our AI test automation framework 2 months ago that got a decent amount of traction ( https://news.ycombinator.com/item?id=43796003 …

Qwen team shows how parallel streams of inference-time thinking tokens could be far more efficient than a serial stream. Compared to scaling parameters alone, the same performance …

The small VLM (Moondream) decides when interface changes / its actions no longer line up. We say 100% open source because all of our code (test runner and AI agents) is completely …

This is definitely top of mind for us! A lot of ways to potentially approach it. We want to make sure the test case execution works really well so our focus is there but also want …