Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step

jdkoeck•about 1 hour ago

I trailed off a few lines into the README. No human ever edited any of this. « LLM detected, project rejected ».

antoniojtorres•34 minutes ago

Every third post in HN has this same complaint comment. Everybody knows.

petterroea•4 minutes ago

It's better that everyone is loud about it then everyone giving up and being silently irritated. At least if people complain it's possible to read the room

jdlshore•18 minutes ago

I appreciate it when people say something is slop. Saves me from wasting my time looking at it.

How many slop ideas have come to the front page, never to be heard from again because the execution isn’t actually any good? I’m guessing most of them.

theturtletalks•8 minutes ago

Just because the ReadMe is slop, doesn’t mean the code is slop. People are starting to make apps for themselves now and open-sourcing them so they’re not putting much thought into the ReadMe or distribution.

This just means ReadMe’s are less important now. I just have my terminal agent dig into the code and tell me what features are there. If the app is actually useful.

Even before AI, there were so many projects with subpar ReadMes, no screenshots, etc. But once you use the software, you realize how good it is.

Source: I maintain a massive collection of open-source alternatives and quality of open-source alternatives have increased a lot

soulofmischief•24 minutes ago

And every comment on HN calling out vibe-coded slop has this same complaint comment in turn. OP has an actual complaint, your complaint is just "stop complaining".

alex_suzuki•about 1 hour ago

I stopped reading at “The honest caveat”…

mmastrac•about 1 hour ago

I'd be interested to see if using DiffusionGemma-as-Jev helps as you can feed the image directly into the model and it'll make decisions based on the image embeddings.

nowittyusername•about 1 hour ago

I had a long talk with chat gpt about this today as well. I think its duable and prolly not too hard either, also you could do lotsa funky stuff with stitched frames of a video in one 4x4 grid for example and send that as one image for analysis. that way temporal understanding can be had for fractions of a second by jev... also because vlm works in pixel space you can get around the whole state machine issue as well, so many possibilities...

Zaraif13•about 2 hours ago

How does it do on OSWorld-verified? Recently read that even Fable 5 is just at 85% .

jgilias•about 1 hour ago

This probably throws a spanner in the wheels there:

> Every piece of reasoning the frontier model does for free has to be rebuilt here as deterministic state.

EDIT: Not to shit on this though. I totally believe that some smart mixture of LLM-reasoning + Jev-style + determinism is going to be pretty amazing.

john_minsk•about 2 hours ago

Super cool. Hope waitlist will move soon. I have a use case for it too.

are you the author? If so - what are your notes on using Jev in this scenario?

jasonjmcghee•about 2 hours ago

Did you do the follow up questions? I was invited within a few hours of joining today.

It's also now on openrouter and cloudflare

baxtr•about 2 hours ago

Same here. 8h hours later I was in.

sroussey•about 1 hour ago

Curious about people’s experience here. I am working on a small model, verify by jev, and escalate to big model. Some cases, the small model is not a model but some regex.

cheap-confirm-escalate

Using jev as the confirm step.

Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step

⚡ Community Insights

Discussion (10 Comments)Read Original on HackerNews