Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why the simplest desktop agent abstraction wins

bytebot.ai

Post reply on HN
Print view View original

11–17 of 17 posts

Re: Why the simplest desktop agent abstraction wins

#11

Post by atupem »

latexr wrote: post #5
atupem wrote: post #3

Earlier quoted context omitted.

Lots of interesting issues: - The agent has a tool to set it's task to 'completed', 'failed', or 'needs_help', with the last one being a option for human in the loop scenarios. Sometimes the agent gets lazy and says it needs help prematurely. - Additionally, the agent can create subtasks for itself, either to run immediately, or to schedule in the future. Here it again can call that tool a bit too eagerly, filling du…

> showing flashes of brilliance A “flash” of anything is also called a fluke, or a coincidence. The dumbest moron can have a flash of brilliance on occasion. So could a random word masher. Consistency is what matters. > and we're gaining more and more conviction that this is the right form factor Are we? Who’s “we”? Because it looks to me like the LLM approach is lacklustre if you care about truth and correctness (wh…

Agreed, and the consistency has improved over time. I remember only a 9 months ago struggling to get a browser agent to accurately click on a checkbox. The growth trajectory is what has us excited.

"We" are a YC-backed startup: https://www.ycombinator.com/companies/bytebot.

Re: truth and correctness, their are different tolerances depending on the type of task.

Re: Why the simplest desktop agent abstraction wins

#12

Post by atupem »

teruakohatu wrote: post #7
atupem wrote: post #3

Earlier quoted context omitted.

Lots of interesting issues: - The agent has a tool to set it's task to 'completed', 'failed', or 'needs_help', with the last one being a option for human in the loop scenarios. Sometimes the agent gets lazy and says it needs help prematurely. - Additionally, the agent can create subtasks for itself, either to run immediately, or to schedule in the future. Here it again can call that tool a bit too eagerly, filling du…

What is your business model?

We're working with design partners as forward deployed engineers, helping setup Bytebot on their infra and tackle use cases.

We'll be launching a self-serve cloud platform soon!

Re: Why the simplest desktop agent abstraction wins

#13

Post by atupem »

lelanthran wrote: post #8
furyofantares wrote: post #6

Earlier quoted context omitted.

This one isn't for coding, they mention in the post that coding agents thrive in custom tool-use environments.

> This one isn't for coding, they mention in the post that coding agents thrive in custom tool-use environments. Well, that is why I am skeptical and said >> I'm still waiting for AI/LLM's to be posing a danger to jobs other than those in software development and the arts. The goal of this product is admirable but, I feel, lacks some grounding: doing screenshots, then converting those images to text, then processing,…

I respectfully disagree! There's a lot of opportunity behind keyboard + mouse + screen.

In a way Bytebot is a maximalist bet on the growth and improvement of multi-modal LLMs. I firmly believe that in a short period of time, the token cost will drop, while the capability increases (both dramatically). It's still uncertain, which makes it a great asymmetric bet.

We don't do any sort grounding or image conversion, and we offer a handful of tools. I'll go into more detail in my next post.

Re: Why the simplest desktop agent abstraction wins

#14

Post by atupem »

lelanthran wrote: post #9
atupem wrote: post #3

Earlier quoted context omitted.

Lots of interesting issues: - The agent has a tool to set it's task to 'completed', 'failed', or 'needs_help', with the last one being a option for human in the loop scenarios. Sometimes the agent gets lazy and says it needs help prematurely. - Additionally, the agent can create subtasks for itself, either to run immediately, or to schedule in the future. Here it again can call that tool a bit too eagerly, filling du…

See my comprehensive reply downthread (it's very long, you cannot miss it). While I am skeptical due to already having explored this for SMME Line of Business applications, I wish you all the best of luck. My approach is to simply build a new system from the ground up that can take advantage of structured IO. [EDIT: send me a message with a link to a post about your product (or this blog), I'll connect with you on li…

Will do!

Re: Why the simplest desktop agent abstraction wins

#15

Post by soulofmischief »

clbrmbr wrote: post #10

Does anyone have experience getting agents to understand terminal applications? Like, in general an arbitrary ncurses application. A more specific case I’ve struggled with is output from a long-running program like ping. You’ve got to know when to terminate.

I wrote a terminal-based falling sand game in rust and incrementally fed the entire screen output to a multimodal LLM (for better generalization) and also got it to attempt to generate interesting initial conditions by spitting out raw characters.

Re: Why the simplest desktop agent abstraction wins

#16

Post by noman-land »

clbrmbr wrote: post #10

Does anyone have experience getting agents to understand terminal applications? Like, in general an arbitrary ncurses application. A more specific case I’ve struggled with is output from a long-running program like ping. You’ve got to know when to terminate.

Instead of telling the agent to wait for something like ping, have it write a script to do it and then have it run the script.

Re: Why the simplest desktop agent abstraction wins

#17

Post by teruakohatu »

atupem wrote: post #12
teruakohatu wrote: post #7

Earlier quoted context omitted.

What is your business model?

We're working with design partners as forward deployed engineers, helping setup Bytebot on their infra and tackle use cases. We'll be launching a self-serve cloud platform soon!

Your profile has no contact details. Feel free to reach out for me if you want some feedback.
Post reply on HN