Hacker Newsnew | past | comments | ask | show | jobs | submit | frangonf's commentslogin

As a former EE, attention was all I needed to not get zapped.

:groan:

I will remember today with a smile in face as the day I met Beany[0].

[0] https://beanshell.github.io/beany.html


"Beany can be bad" "LGPL"

I mean, LGPL isn't THAT bad, but made me chuckle.


That needs to be updated... Beany is ALv2 :)

There's also this setting here which I have set to 'Do not train on my content' even though I trust it the same as the 'allow training' one...

https://privacy.openai.com/policies/en/?modal=take-control


Thx for the link, hadn't seen this one, submitted also

I've imagined bugs releasing magic smoke faster than usual.

Openclaw creator Peter Steinberg was in talks with Zuck at the beginning of the year before choosing to work for Openai.

I think Meta limiting factor for this product was lack of agentic capable models which they fixed now with aggressive RLHF focused data gathering.


RLVR

Around 20s saved by eating on those \n\n.

For evaluating subs you have to put the money and try by yourself to get your own measurement, since the subs quotas and new models are always changing and overall info is unreliable.

20$ of Codex/Google/Chinese gives you some fair amount of usage to test them, and Opencode Go for 10$ lets you try a good amount of models with good quota. I don't use Openrouter because it gets more expensive than the subs, but for testing, swapping and being completely independent, a proxy service is the best solution.

About benchmarks, I usually agree with DeepSWE. Looking at usage rankings of models in Openrouter is also a good signal.

For changing models locally I just use pi (used also opencode in the past) or if the sub does not allow login in external harnesses I just use whatever cli they have, last year there were differences but today they are all good enough for my needs and have basically the same features.


I would start by using AI to port the tangled mess into as much a tidy IaC as possible, with git backed declarative config tools, to prepare the safe ground where agents have context, can get loose and easily review, lint/check or test in throwaway VM before applying it.

A fleet of Openclaws (or equivalent) with control of machines for 100% hands off management seems like a russian roulette to me as of today, but a 90% handoff to AI for reviewing current config of X in our system, reading docs and configuring a deterministic tool is achievable and somewhat safe as you can easily review and trace what has been done.


I had the project already starred, I lurk around the sandbox space from time to time, and the project it's a few months old and was already discoverable and in a usable state before today.


Still, over 3,000 stars so quick? It's just weird.


The earliest repository commits and initial public announcements show this date: March 17, 2026.


Everything you think will be recorded via neural decoding from your meta smart glasses and apple neural headsets in the near future.


I’d imagine some people would actually find that useful if they offered a backup and restore feature.

No more “why did I come in this room again?” moments.


Don't fucking encourage this lol


Don’t look at me. I won’t even put a TV online because they want to watch me back.

What I do know, however, is that most people seem to be willing to give up everything for a little convenience.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: