Viewing profile — linuxhansl
linuxhansl
HN member- Joined
- Wed, Aug 18, 2010, 9:55 PM UTC
- HN karma
- 3,340
- Public activity
- 760 items
- HN profile
- View on Hacker News ↗
About linuxhansl
No profile information was provided.
Recent public activity
-
comment
Comment #49217684
Disclaimer: I use AI at work and for some projects at home and find it really useful (as long as you know when and how to use it) With that said... It's funny how we went from "vib…
-
comment
Comment #49191395
I'm honestly surprised he held on for so long. Can't tell if it made a difference, though, as I haven't used Twitter for about decade. I'm having a somewhat hard time understanding…
-
comment
Comment #49164554
While I agree on some level, this not a great comparison. A compiler/linker/etc is an algorithmic, precise, verifiable, repeatable, debuggable, etc, etc, process. Using an LLM is a…
-
comment
Comment #49157522
I almost feel that we have a new generation of the "script-kiddie". People without much (or any?) knowledge of software engineering using outside tooling to do "stuff" they wouldn'…
-
comment
Comment #48844253
Yes... And, perhaps the political comments here are a reasonable reaction to the misguided political influence that shaped grok. How can we trust grok after this? At least it will …
-
comment
Comment #48758675
Not much one can do I fear... Install f-droid and all kinds of 3rd part apps now. Install GrapheneOS. (I'm guilty of not having that done that,yet :( ) Sign the petition ( https://…
-
comment
Comment #48757561
What Google is doing is shameful. One of the promises of Android was being more open than the restrictive Apple ecosystem. Now that they reached penetration they do the switch - un…
-
comment
Comment #48564654
How qwen3.6:27b compare to qwen3.6:35b-a3b (MoE) in your experience (if you tried). I find the dense models are way too slow on my H/W.
-
comment
Comment #48564624
I soooo wish that to be true. Alas, in my experience it is not... Yet. What is true is that it gets easier and faster to run local models. With QAT (quantization aware training), t…
-
comment
Comment #48436374
This is really awesome. I tried my test-task (generate a Python wrapper for a fairly complex C-interface) with gemma4:26b-a4b-it-qat. And for the first time it would just do it, wi…
-
comment
Comment #48426575
Thank god some sanity prevails. Adding these to the index immediately would force passive index funds (multiple trillions of $) to buy this stock, and thus not allow the market to …
-
comment
Comment #48392390
I use Claude every day. Often for multiple hours a day. Basically doing my job not worrying how many tokens I spend (as in too many or too few). This is a pretty complex code base …
-
comment
Comment #48375337
I am using Opus 4.x at work, and these "smaller" (20-80bn, 3-4bn active) models at home. Unfortunately there is no comparison, yet (IMHO anyway). With Opus I can work, trust its de…
-
comment
Comment #48311917
Please, not the SAT! My son is prepping for the SAT and I am helping him. I studied physics and computer science, and was a advanced math A+ student... IMHO: The SAT is useless, so…
-
comment
Comment #48282064
Good. Just naming things differently does not work in other countries. If it quacks like a duck, swims like a duck, and looks like a duck, then it probably is a duck.
-
comment
Comment #48250381
Other countries paying $10,000's to educate people who then want to apply this knowledge in the US. US reaction: "Nah." Besides, we are talking about legal immigration here. I don'…
-
comment
Comment #48241261
Are we purposefully dumbing down the country now? Sure, some things are trade-secrets or national security issues or whatnot, but those are already not shared. More than militarily…
-
comment
Comment #48076330
> Wrong the way it would be wrong to predict that if you set your kitchen on fire, the result will be a renovation. This might be favorite metaphor ever, and one I'll quoting in th…
-
comment
Comment #48044507
I guess it all depends on what you use it for. I work on database optimizers and other database related stuff, and I can assure Claude Code - with all the highest settings - does m…
-
comment
Comment #47917892
The size of the KV cache (context stored) is proportional to the number of layers of the model and number of "hidden dimensions". For a 400B model it could be 30-60GB for just an 8…
-
comment
Comment #47917382
I am fascinated by this and similar research (RotorQuant, etc). It seem by next year we will be able to run this year's largest models on last year's hardware. :) Maybe we won't ne…
-
comment
Comment #47781765
Hmm... Sure, if you do not need a database then do not use a database. Don't use a sports-car to haul furniture or a garbage truck as an ambulance. For the use case and scale menti…
-
comment
Comment #47781621
So Cal.com favors security through obscurity. Open Source was always open to "many eyes" in theory exposing itself to zero-day vulnerabilities. But the "many eyes" go for the good …
-
comment
Comment #47707083
Good. Now leave TikTok and Facebook as well. People who care will find out what you are up to, and people who don't won't see you on social media anyway. I left Twitter, Facebook, …
-
comment
Comment #47459367
How much many more wars over gas or oil do we need to finally just take the energy that (for the most part) is available locally and renewable?! The petrol era is coming to an end.…