maggreenWAI

74 karma · joined October 10, 2023

maggreenWAI··on Show HN: I wrote an open-source browser alternative for Computer Use for any LLM

You can just extend this e.g. with adding data to database, sending notifications, extracting specific data format ect... make sure to also accept your added function when its called in act() https://github.com/gregpr07/browser-use/blob/main/src/contro...

maggreenWAI··on Show HN: I wrote an open-source browser alternative for Computer Use for any LLM

Let's say in 1 year, more agents than humans interact with the web.

Do you think: 1. Websites release more API functions for agents to interact with them or 2. We will transform with tools like this the UI into functions callable by agents and maybe even cache all inferred functions for websites in a third party service?

maggreenWAI··on Show HN: I wrote an open-source browser alternative for Computer Use for any LLM

Next step is to represent also the structure of the HTML tree in the extracted elements for better understanding, maybe images are then less needed.

maggreenWAI··on Show HN: I wrote an open-source browser alternative for Computer Use for any LLM

Context length + API cost is right now main bottleneck for huge HTML + CSS files. The extraction here is already quite efficient but still: with past messages + system prompt + sometimes extracted text + extracted interactive elements you are quickly already around 2500 tokens (for gpt-4o 0.01$).

If you extract entire HTML and CSS your cost + inference time are quickly 10x.

maggreenWAI··on Show HN: I wrote an open-source browser alternative for Computer Use for any LLM

A) For Mind2Web: because there are multiple ways to reach a goal state - any thoughts how to evaluate if a task was successful? Should we let the LLM/ other LLM evaluate it?