Viewing profile — Farmadupe
Farmadupe
HN member- Joined
- Thu, Jan 21, 2021, 4:48 PM UTC
- HN karma
- 102
- Public activity
- 39 items
- HN profile
- View on Hacker News ↗
About Farmadupe
No profile information was provided.
Recent public activity
-
comment
Comment #48859770
I'm totally feeling you here as well. Fable is definitely quicker to first output token on `claude.ai` (ie less internal reasoning tokens being generated), and given how much more …
-
comment
Comment #48851792
Yes this is an extremely well known result for exactly the reason you guessed. It's not just abcktracking, asking an LLM to present a conclusion and then justify is also an excelle…
-
comment
Comment #48752628
Is it too cynical to read the first quote as "when openai catch up, we will restore fable 5 to subscription plans"? In other words, they're saying "We know have a monopoloy and we …
-
comment
Comment #48677964
2 and 3 bit quants are often closer to gibberish than hallucination, and that'll happen regardless of context. I shouldn't claim too much, I haven't tried GLM5.2 at 2/3 bit quantiz…
-
comment
Comment #48342400
It's amazingly vacuous isn't it? I think the most interesting read was the fact that they were surprised llama.cpp crashed when they used a bad set of commandline arguments. Althou…
-
comment
Comment #48093802
I'm not sure there's a one-stop shop for this at the moment. I think the process is: * Have a box with sufficient spare (V)RAM -- probably 8G for simple categorization with qwen3.5…
-
comment
Comment #48093655
Yup, especially when for a lot of us, the price of the frontier subscription has become a cost of doing business over the last 6 months. If you're already doing big boy stuff with …
-
comment
Comment #48093445
The latest rounds of open weights vision language models are incredibly good. Like, massively good. Open weights vision capabilities trade blows with frontier models. Over the last…
-
comment
Comment #48026541
If it helps, I mean it in a really literal sense. qwen3.6 27b is currently $3.20 per million tokens on openrouter right now which is way overpriced. As good as the 27b is, kimi k2.…
-
comment
Comment #48025077
I wonder if for a model that small with a permissive license it might not be worth their time to host a commercial grade inference stack? Might be easier to chuck it over the fence…
-
comment
Comment #45143664
Using protobuf is practical enough in embedded. This person isn't the first and won't be the last. Way faster than JSON, way slower than C structs. However protobuf is ridiculously…
-
comment
Comment #40815435
I feel like there's a semi-philosophical question somehwere here. Recursion is clearly a core computer science concept (see: many university courses, or even the low level implemen…
-
comment
Comment #39073353
The author is making a deliberate point about undefined behaviour in the article. Hence them not executing worked examples. In fact, by not doing so they are making a subtle implic…
-
comment
Comment #37968605
FWIW, 85k 4-input luts is huge by the standards of any softcore with "micro" in the name. It comfortably surpasses the capacity of most of the Actel aerospace FPGAs that I tend to …
-
comment
Comment #37968553
...could be named for how much space is left after that soft core has been instantiated.
-
comment
Comment #37453986
Steppers are super optimized for being super precise and easy to controle while being (relatively) cheap to build. They have weird "trick" geometry that means you can move the roto…
-
comment
Comment #37453950
Out of interest, what could make such a design better than a traditional inductive motor? Such motors already suffer inductive losses, and do not need slip rings or brushes, and pr…
-
comment
Comment #37453919
I know press releases never describe anything that's actually novel, but it looks like they're just describing an asynchronous induction motor? I'm wondering if this release is imp…
-
comment
Comment #37181615
Download counts don't mean very much here as I'm fairly sure both crates are common transitive dependencies. Or in other words, millions of programmers aren't individually choosing…
-
comment
Comment #37102051
Im assuming the "halt and catch fire" thing is only really possible on pre-microprocessor machines built of discrete components, where the individual parts are small enough to over…
-
comment
Comment #36509339
just a few drive-by comments: First and most important, the title claims these are safety-critical rules, but the conclusion says that they are only being used on mission-critical …
- comment
-
comment
Comment #36270729
Considering it's allocation-free, maybe it's an ultralight/ simulator for checking large quantities of compiler output? (i.e no VM to create and destroy for every testcase) Or the …
-
comment
Comment #35032962
Honestly I think your observation is mostly right... if you don't have a hard performance requirement, then rust probably isn't the best language to write your code in...
-
comment
Comment #34092196
GP might have been referring to undefined/invalid behaviour (whether in the language or in some OS syscall or whatever). After the demons came out of your nose you can never fix th…