HackerTrans
TopNewTrendsCommentsPastAskShowJobs

mirekrusin

5,564 karmajoined 12 वर्ष पहले
https://github.com/mirek

https://github.com/preludejs

Submissions

Ask HN: Year of Linux Desktop is fun with LLMs

6 points·by mirekrusin·28 दिन पहले·3 comments

Facebook's Flow is being ported to Rust

github.com
3 points·by mirekrusin·2 माह पहले·0 comments

comments

mirekrusin
·कल·discuss
And now you’re ready to level up with motorbike jump.
mirekrusin
·4 दिन पहले·discuss
It's simple: close weights = not welcome.
mirekrusin
·4 दिन पहले·discuss
Open weight models should have GPL-like license where it says if you train model on it, it needs to be open weight as well.
mirekrusin
·6 दिन पहले·discuss
Give it few years and they'll get LED colors and we'll see them in "I'm lovin it" formation.
mirekrusin
·7 दिन पहले·discuss
it's not overpriced but high-priced looking from other countries and mostly not a markup, normal considering median wages.
mirekrusin
·7 दिन पहले·discuss
In others it's pizza night for family or half a bill for sushi dinner, so what?
mirekrusin
·13 दिन पहले·discuss
What's the difference between this and Public Domain/CC0 from PoV of labs and vibers?
mirekrusin
·15 दिन पहले·discuss
Closed weight models are a result of philanthropy by some private investors.
mirekrusin
·16 दिन पहले·discuss
"for the benefit of all humanity *"

* with big pockets
mirekrusin
·20 दिन पहले·discuss
Banning models in US just strengthens competing states, ie. China.
mirekrusin
·21 दिन पहले·discuss
Yes, exactly, quite shocking, if something like this is true, as NSA (!!) director you keep it quiet, right?
mirekrusin
·21 दिन पहले·discuss
Mythos and other models are not brute-forcing passwords (and with this analogy passwords, ie. systems are the same).

We're not talking about dogs, but LLM systems.

Mythos is not exploring entire solution space either.

Usually looping is solved by repetition/frequency/presence/n-gram penalties/DRY/min-p sampling, not temperature but we're not talking about small models that have those classes of issues here.
mirekrusin
·21 दिन पहले·discuss
If mythos can break into almost all of their classified systems in hours then other models including opus, gpt, gemini and large open weight models can do so as well, maybe you'll have to double hours or it may become days, but they also will, there is no "maybe" in here.

State sponsored, non-public penetration fine tunes (of possibly public ones) likely can do it even faster.

Unsupervised penetration RL loop is ideal setup similar to optimization one – it's relatively easy to gain function on it.
mirekrusin
·21 दिन पहले·discuss
This suggestion fails for values that can be null, need to be mutable or need references from multiple places etc – it's not "just performance penalty".

Go has a problem, "just remember to always do X, never Y" patterns can't be guaranteed across all libraries you use, can't be enforced, can be violated for good reasons, other patterns and as a mistake etc etc.

Shame because otherwise it's a great language, but some mistakes are just no-go.

So close indeed.

They need Go 2 with *T and ?*T - that would be nice language to use.
mirekrusin
·22 दिन पहले·discuss
Did they rewrote WebKit in Rust or not yet?
mirekrusin
·22 दिन पहले·discuss
That reply was AI written.
mirekrusin
·23 दिन पहले·discuss
Did I get it wrong or the first link has dataset with 30 entries only?
mirekrusin
·24 दिन पहले·discuss
Wikipedia is a lot of data as well but we manage to do it, no?
mirekrusin
·25 दिन पहले·discuss
I don’t understand why there isn’t public dataset for reasoning that can be improved by humans/llms like Wikipedia (ie with auto judging contributions etc).
mirekrusin
·25 दिन पहले·discuss
So the goal is to evaporate it with minimum number of shots?