AI Language Models & Transformers - Computerphile

What people said

mhast · 2025-02 · Recommendation

If you want to get a better understanding of this I recommend playing around in the "chat playgrounds" on some of the engines. The Google one allows for some free use before you have to pay for tokens. (Usually you can buy $5 worth of tokens as a minimum and that will give you more than you can use up with manual requests.) [LINK] This UI allows you to alter the system prompt (which is usually hidden from the user on eg ChatGPT) and change to different models and change parameters. And then you give it the chat input similar as any other site. You can also install a program like "LM Studio" and that will allow you to download models (through the UI) and run locally on your own machine. This gives you a similar interface to what you see in the Google AI Studio but you run it locally. And with downloaded models. (The model you download is the actual LLM which is basically very large amount of parameters you combine with the input tokens to get the next token the system outputs.) For a more fundamental introduction to what all these systems do there are a number of Computerphile videos which are quite informative. Unfortunately I can't find a good playlist of them all but here's one of the early ones. (Robert Miles is in many of them.) [VIDEO]

Read the original HN comment ↗

FranklinMaillot · 2023-05 · Recommendation

Those Computerphile videos[0] by Rob Miles helped me understand transformers. He specifically references the "Attention is all you need" paper. And for a deeper dive, Andrej Kharpaty has this hands-on video[1] where he builds a transformer from scratch. You can check-out his other videos on NLP as well they are all excellent. [0] [VIDEO] , [LINK] [1] [LINK]

Read the original HN comment ↗

cercatrova · 2022-08 · Recommendation

This video by Computerphile is a great overview of transformers and how we got to this point [0]. Basically the networks we used before, recurrent neural networks, "forgot" prior information so they're not good at long tasks. The transformer architecture however does not forget (or at least as easily). [0] [VIDEO]

Read the original HN comment ↗