mkemp Verified User
-
mkemp reacted with to JedRothwell’s post in the thread The LENR-CANR ChatGPT is ON LINE!.
As artificial intelligence developers run out of data to train their models, they are
turning to “synthetic data” — data made by the A.I. itself.
Given the state of the art of AI, that cannot end well. It is, however, hilarious.
Consider this. AI generated… -
mkemp reacted with to Diadon Acs’s post in the thread Offline Models for Apple hardware(CoreML + MLX) Local Inference.
[…]
Yes, going to need above 16GB+ GPU to run the larger models.
I'm excited by some of the new hardware coming online from Nvidia and in particular Groq's chip architecture.
One solution to your problem is to spin up rented hardware through one of the… -
mkemp reacted with to Alan Smith’s post in the thread Offline Models for Apple hardware(CoreML + MLX) Local Inference.
You might find this paper about datasets interesting. AI and LENR - The Bots Get Busy. -
mkemp replied to the thread Offline Models for Apple hardware(CoreML + MLX) Local Inference.
Been a while but finally got back round to this, i've found Ollama to be a good project for running models locally, and you can use the continue plugin in vscode for co-pilot like experience. My Macbook Pro M2 16GB is probably too constrained to go above… -
mkemp reacted with to Diadon Acs’s post in the thread The “Thunderstorm” reactor as another potentially easy to replicate, and very useful, possibly LENR device.
[…]
I appreciate your passion and interest in abundant energy.
However, I do think Malcolm Bendall is a kind of a false messiah of science when he disregards so much of it's collective body f work.
Charisma and money can take a man so far, but how could a…