AlexeyBrin

macOS has a different dev culture than Linux, but you can get pretty close if you install the Homebrew package manager. For running LLMs locally I would recommend Ollama (easy) or llama.cpp. Due to th…

At least for now, seems to be available only for the 14" MacBook Pro. I want a 16" M5 MacBook Pro so I will wait ...

Unfortunately someone with advanced dementia does not know if she has eaten or not. Most of the time there will be no eating, unless someone else puts food in your mouth.

Would be great if they can release it on YT fully. I doubt anyone buys it today since it is so dated, but would be interesting from a historical perspective.

The conclusion of the original study https://www.thelancet.com/journals/eclinm/article/PIIS2589-5... contradict the title of the article linked here: Influenza vaccina…

"The text discusses and implements a self-hosting compiler for CP/M on the Z80."

I read it as "no Gen AI" was used to write this book.

I second this, would be great if someone did a long form video interview with the author.

If you don't get an answer here, try to contact the author directly through his website, he is pretty responsive.

https://archive.is/jVxOs

If you want to be 100% sure you need to run/use a local LLM. Also it seems that this data retention/training does not apply to the API. I think both Anthropic and OpenAI do not train on ente…

Have you considered that some of the people that are against AI are worried about a potential loss in the human experience like AI replacing writers, painters and thinkers or at least diluting the hum…

Maybe the LLM forgot to write the tests ?

The thing is a human can produce only so much code in a given time, with LLM(s) one can produce x times the same amount of code. Are you able to read, understand and clean up 5x or 10x as much code a…

Just make sure to keep VDDIO powered when 5V is applied to any GPIO pad, otherwise the pad will be damaged. And be sure to read the relevant sections in the updated datasheet. This is great …

You are reading too much into my comment. My point was that the test (a Space Invaders clone) used to asses the model is irrelevant for some time now. I could have gotten a similar result with Mistral…

A gaming PC with an NVIDIA 4090/5090 will be more than adequate for running local models. Where a Mac may beat the above is on the memory side, if a model requires more than 24/32 GB of GPU …

Most likely its training data included countless Space Invaders in various programming languages.

The end of the article is baffling: While these changes may not have an immediate impact, they hint at a future where Indian IT professionals and outsourcing firms could face more hurdles if Tru…