Viewing profile — techbruv

At a previous job, I recall updating a dependency via poetry would take on the order of ~5-30m. God forbid after 30 minutes something didn’t resolve and you had to wait another 30 …

I don’t understand the argument “AI is just XYZ mechanism, therefore it cannot be intelligent”. Does the mechanism really disqualify it from intelligence if behaviorally, you canno…

> So it will not get worse in performance but only faster A bit confused by this statement. Speculative decoding does not decrease the performance of the model in terms of "accurac…

Some other good resources: [0]: The original paper: https://arxiv.org/abs/1706.03762 [1]: Full walkthrough for building a GPT from Scratch: https://www.youtube.com/watch?v=kCc8FmEb…

The idea that GPT-4 is 1 trillion parameters has been refuted by Sam Altman himself on the Lex Fridman podcast (THIS IS WRONG, SEE CORRECTION BELOW). These days, the largest models…

> "We then train several models from 400M to 15B on the same pre-training mixture for up to 1 × 1022 FLOPs." Seems that for the last year or so these models are getting smaller. I …

ChatGPT and other LLMs for that matter are most definitely not using beam search or greedy sampling. Greedy sampling is prone to repetition and just in general gives pretty subpar …