Viewing profile — xlayn

People who argue against AI are the same people arguing against the car because of horses... This is going to open a whole field of jobs for... ... ...... someone... but let's not …

Assumming it's true, half a cup of rice and tortillas it's a formula for a lot of nutrients deficiency + lack of proteins make the body start pulling it from muscles in order to re…

I have see a lot of "run using cpu" or using 1gb of ram... and the short answer is sure, you can run it in 1mb of ram, or in a 286, it will just take a couple of years to produce t…

Let's make the whole working/colaborating environment a training input for the model, we have to replace each and every link of human everywhere, think about the stock prices... ye…

get your eyesight check, at some point in life I was having difficulties staying focus and even started having headaches... and I needed prescription glasses... Also very important…

I would like to argue that trying to provide a free service is non achievable, most of the time it will drill down to ads, people are already paying electricity and time in ads. If…

X402... I was not aware, I had this idea of making HTTP connection depend on a monero transaction, the monero transaction should take around 3 secs of the average computer/cellphon…

because we need quadratic energy increase to increase speed linearly, that's why a 200hp car is not twice as fast as a 100hp one. Gee let me elaborate a bit more... if the 100hp ca…

I want to rush to git clone, but as things are, the odds are extremely high that this kind of things that are too good to be real are honeypots and something there will compromise …

Another perspective, if you compare it to two years ago, how much more expensive is it and how much better? we are paying the sAIm Taxltman. Just see, you could buy the steam deck …

I created a patch for llama.cpp to store on disk instead of deleting the kv cache as well as the checkpoints... there is this bug on llama.cpp if you have more than one instance go…

I hope someone at jetbrains with enough power read what we are saying in this thread.... changes for the sake of changes are bad... when they did the change to the "new UI" I kind …

I use copilot for work, and I have this fight with models all the time because the model has an urgency to get things done, Sometimes I need to explain an issue, elaborate on the c…

Ohhhh geee!!! I just applied the patch to my local git copy. You need to use the model on the PR that he submitted, the model is particular because it has extra information that al…

If anthropic is doing this as a result of "optimizations" they need to stop doing that and raise the price. The other thing, there should be a way to test a model and validate that…

I had a 6950 on my pc from when I built the thing... and then bought the 7900 for $5xx, that allows me to run more models, and then I saw the "Radeon AI PRO" and after a couple of …

I updated the results, with just the Devstral part, but ran the full suite for it, and posted all the results file as well as a script to re-run the process. The results are more s…

Fair point on the writing style, I used Claude extensively on this project, including drafting. The experiments and ideas are mine though. On the prior art: you're right that layer…

You can check here the results for Devstral, speed limits me, but these are the results for the first 50 tests of the command # Run lm-evaluation-harness lm_eval --model local-chat…

I explored that, again with Devstral, but the execution with 4 times the same circuit lead to less score on the tests. I chat with the model to see if the thing was still working a…

The other interesting point is that right now I'm copy pasting the layers, but a patch in llama.cpp can make the same model now behave better by a fact of simply following a differ…

I published the results for devstral... results folder of the github https://github.com/alainnothere/llm-circuit-finder/tree/main... I'm using the following configuration --tasks g…

I replicated David Ng's RYS method ( https://dnhkng.github.io/posts/rys/ ) on consumer AMD GPUs (RX 7900 XT + RX 6950 XT) and found something I didn't expect. Transformers appear t…

There is a performance improvement as per [0][1] the memory speed went up from 5500MT/s to 6400. [0] https://www.steamdeck.com/en/tech [1] https://www.steamdeck.com/en/tech/deck