Juminuvi · HackerTrans

2 месяца назадdiscuss

I've only read this blog and not the paper so maybe they go into more detail there and someone can correct me, but they frequently bring up the model's ability to detect or at least the model activations hint it can predict when it's being tested. I can't help but wonder, as they build these larger and larger models, where they could be getting "clean" training data, untainted by all these types of blog posts and the massive numbers of conversations they spawn? If the models ingest data like that wouldn't it make sense they'd be inclined to have more activations attuned to questions they appear adversarial?

Juminuvi

4 месяца назадdiscuss

I think the UI is pretty slick but agree having a TUI option as well would be awesome. Everything in wsl management (import, export, register, compact, etc) can be done with shell commands I believe so a tiny performant TUI might be a straight forward thing for op to add in the future though.

Juminuvi

4 месяца назадdiscuss

Very much agree with the idea of red/green TDD and have seen really good results during agentic coding. I've found adding a linting step in between increases efficiency as well and fails a bit faster. So it becomes..

Test fail -> implement -> linter -> test pass

Another idea I've thought about using is docs driven development. So the instructions might look like..

Write doc for feat/bug > test fail > implement > lint > test pass

Juminuvi

4 месяца назадdiscuss

100% agree. Hopefully etiquette will catch up if enough folks talk about this.

Side note, the number of comments here from people who clearly didn’t read the article is impressive

Juminuvi

7 месяцев назадdiscuss

I know you say you don't use the paid apis, but renting a gpu is something I've been thinking about and I'd be really interested in knowing how this compares with paying by the token. I think gpt-oss-120b is 0.10/input 0.60/output per million tokens in azure. In my head this could go a long way but I haven't used gpt oss agentically long enough to really understand usage. Just wondering if you know/be willing to share your typical usage/token spend on that dedicated hardware?

Juminuvi

10 месяцев назадdiscuss

I noticed something similar. I asked it extract a guid from an image and it wrote a python script to run ocr against it...and got it wrong. Prompting a bit more seemed to finally trigger it to use it's native image analysis but I'm not sure what the trick was.