HackerTrans
TopNewTrendsCommentsPastAskShowJobs

jawerty

no profile record

Submissions

Ask HN: Is anyone here also developing "perpetual AI psychosis" like Karpathy?

32 points·by jawerty·4 ay önce·30 comments

Show HN: X Timeline Cleaner, block tweets by location from your X timeline

github.com
2 points·by jawerty·8 ay önce·0 comments

Show HN: Ismyceoafraud, figure out how likely an entrepreneur is to commit fraud

ismyceoafraud.com
10 points·by jawerty·geçen yıl·1 comments

Show HN: We're building a desktop app for browser-based AI agents

meha.ai
50 points·by jawerty·geçen yıl·56 comments

Show HN: We're Building a Desktop App for Browser Agents

meha.ai
6 points·by jawerty·geçen yıl·5 comments

Complete web browser automation via AI prompting

twitter.com
1 points·by jawerty·2 yıl önce·1 comments

comments

jawerty
·4 ay önce·discuss
Yea there could also be an issue with learning how to hand hold an AI vs working on how to actually engineer good solutions. Maybe one feeds into the other since we're not getting off the AI train...
jawerty
·4 ay önce·discuss
Agreed. However, I'm worried the productivity hack AI gives us might effect the "what" negatively.
jawerty
·4 ay önce·discuss
Excited to use this been using unsloth models for the past couple years
jawerty
·8 ay önce·discuss
Currently working on training language models steered towards certain "states of consciousness".

I have a model trained on publics datasets tied to brainwaves and/eye tracking and text comprehension (have this working well enough to experiment). Now I am training an adapter for various llm architectures to generate text steered to certain neural oscillation patterns (let's call them "states of consciousness" for brevity). I also have a 'rephraser' that rephrases text to elicit these certain states of consciousness. Overall experimenting with creating an suite of tools off my findings with how text relates to the eigenmodes of consciousness. My theory is once I do this I'll be able to do some...interesting things with "AI" agents. lmk if you want to talk about it if you're someone with knowledge in neuroscience/ML. My background is as a Software/ML Engineer so I could use additional thoughts. I do wish I could send a Github/docs which I will soon but this is currently a private project seeking investment for various research/public/private sector applications.
jawerty
·12 ay önce·discuss
If anyone wants a free to use research agent try rex I've been building it for a couple months: https://projectrex.onrender.com/
jawerty
·12 ay önce·discuss
If anyone wants a free to use deep research agent check out what i'm working on: https://projectrex.onrender.com/
jawerty
·geçen yıl·discuss
It is not, Meha agent is fully custom except we don’t use our own models we’re using o3-mini for most of the inference
jawerty
·geçen yıl·discuss
Thanks! That’s a great point we’ve been discussing how to deal with sensitive data after the launch. I think a corporate/enterprise version makes sense.
jawerty
·geçen yıl·discuss
awesome that's the same reason why I use it. It's basically a balance between the full html and having the markdown type scrapers that are better for just text. Do you mind if I reach out to you once I set up the Github?
jawerty
·geçen yıl·discuss
Oh damn I will definitely look into open sourcing it and making it a sdk
jawerty
·geçen yıl·discuss
Awesome we just fixed these issues thanks for letting us know.
jawerty
·geçen yıl·discuss
Sooo make your html extremely convoluted, randomized semantics, and a ton of hidden interations (+1 for only using custom web elements). basically make it like youtube. After spending way too much time building browser agents I can assure you this will also defeat Operator as well.
jawerty
·geçen yıl·discuss
Thank you for the feedback. Personally besides using our API server, we would like to find another way to deploy to anyone who has an issue with this/wants to run everything local (not just the client). Also I think if we had a OSS plug and play version where you could enter in your API keys locally it would help us ship to more devs. Would you be interested in this?
jawerty
·geçen yıl·discuss
Great! I will work on open sourcing that on our Github. It's basically a semantic format of html for AI agents to use the browser easily.
jawerty
·geçen yıl·discuss
We have an API server where we execute all the agent reasoning/planning jobs then we stream the browser commands to the client. We mention this in the how it works section on the website. This is the main reason why we have the 5 bot a day limit is because of this. It's cheap for us to run as of now but if anyone would like us to ship a version where you'd use your own api keys (plug n play) locally let us know!
jawerty
·geçen yıl·discuss
Anything improving reasoning chains of though improves planning. Right now the long term ones Art mentioned like logging in have been around 80% while simpler ones have been higher. Right now our main issue is figuring out how to keep the server up :/ we're getting a little more traffic than expected. However, to bump those success rates up (which we need to) we really really need to fine tune additional models which we're planning out right now.

I have a few ideas around that mostly going down the RL route (with a twist) mixed with some knowledge graph work. We'll give an update when we push that!
jawerty
·geçen yıl·discuss
Thanks for letting us know can you email us at [email protected] or dm one of us on discord with more information we're working through all the bug reports in the next couple days.
jawerty
·geçen yıl·discuss
maybe browser AI agent? Good note we didn't think of that.
jawerty
·geçen yıl·discuss
Great question, so right now you can do both. It does work better if you simply enter in the url for your task.

For the url generation we do we have safety checks for the urls however it's simply in the prompting. I would love to hear what sort of safety suggestions you have and/or concerns about this sort of experience. Right now we're still figuring out how best to enable people to utilize agents safely.
jawerty
·geçen yıl·discuss
Interesting can you lmk why you ditched all non native? We're discussing what decision to make on this now.