tangent question: Claude code seems to be very much loved and suggested by most major Chinese LLM using the env vars to change the server. that however means you lose a lot of anthropic tools like auto mode, running shells, monitors/crons. is there a way to get those with non anthropic plans?
And this is why there should be very very unpleasant for manufacturer legislation about allowing access to hardware you buy.
This is a generic problem not limited to automotive industry, though they are a major offender. Locked down android auto, systems, buses, everything is proprietary and you are the whims of the manufacturers decisions
Just as a warning however the vibe coded website doesn't inspire confidence this isn't low quality auto generated AI slop and/or AI managed infra.
Looking into it of course this seems to not be the case, but just wanted to say, don't use generic looking theming that is default of all LLM-generating websites :)
One of my things are that I am an engineer and I build functionality for engineers, this has always been the case. I am bad with visualizing this so the vue framework has helped tremendously with that.
With that said, I hope as well that it is a amazing idea, I am really happy with how it works and performs.
Even though I agree with other commenters that calling out websites as AI slop based on the copywriting and "generic LLM-generated look" is getting tiring, I can't deny that this was my immediate reaction to it as well.
On the other hand, you being on this comment thread and answering questions competently is a huge boost to the project's credibility in my eyes! But once the link disappears from the front page, only one of these things will remain. :-)
It looks alright, I have no issue with it. People just like to hate on things that have zero relevance to the actual product.
It's not like pre-LLM you wouldnt go to Themeforest and see hundreds of designs that were all the same. Now they just call it AI slop, before it was just slop.
I know right, and you would try different themes, go into the code, try to delete footer information that pointed back to the theme maker only to break the structure of everything.
quite brilliant though don't expect any easy therapies out of it yet. there is no known small fragment(ie manufacturable peptides) that bind to PLXNA1 , and the terminal fragment is about 400 amino acids, way more than what can be produced with solid peptide chemistry (100-150 amino).
something I have been wondering about is doing regressive layer specific quantization based on large test sets. ie reduce very specifically layers that don't improve general quality.
This is a very well established idea. It's called dynamic quantization. Vary the quantization bit-width (or skip quantization altogether) on a layer by layer basis, using a calibration dataset.
EvoPress is the first time that comes to my mind, when I think of dynamic quantization.
I've experimented with this with diffusion models with a safetensors - gguf tool I wrote. even with relatively few sample images (~10k, still enough to keep my 3090 spinning for days straight) the benefits are quite noticeable - a smaller file with overall better results.
I mean it works... but it's really ghetto. You have to handle username collisions(or enforce unique usernames). IPv4 should be non free, and that'd cover the costs...
Iran International (Persian: ایران اینترنشنال, romanized: Irān Internašnāl) is a Persian-language satellite television channel and multilingual digital news operation based in London, United Kingdom. Established in May 2017 and reportedly linked to Saudi Arabia.
from wiki
this is just a mouthpiece of the Saudis probably condoned by MI6. take it with a grain of salt.
reply