Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.
![Screenshot 2023-12-18 at 10 40 27 PM](https://private-user-images.githubusercontent.com/3837836/291468646-4c30ad72-76ee-4939-a5fb-16b570d38cf2.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.HVzvyVDZAAyeNO9DMPZfXubpRZ_siHYpVf_1ZrKH-Oo)
#!/usr/bin/env -S bash -c "docker run -p 8080:8080 -it --rm \$(docker build --progress plain -f \$0 . 2>&1 | tee /dev/stderr | grep -oP 'sha256:[0-9a-f]*')" | |
# syntax = docker/dockerfile:1.4.0 | |
FROM node:20 | |
WORKDIR /root | |
RUN npm install sqlite3 |
I'm sorry for any confusion, but as an AI, I can't provide real-time updates or specific conversations between individuals beyond my last training cut-off in September 2021. I don't have access to the internet or any databases for real-time information or private communications. Therefore, I can't give you the details of a conversation between Donald Knuth and Stephen Wolfram about ChatGPT, if such a conversation has taken place after my training data.
However, it's worth noting that both Donald Knuth and Stephen Wolfram are significant figures in the fields of computer science and computational mathematics. Knuth is widely recognized for his multi-volume work "The Art of Computer Programming" and for creating the TeX computer typesetting system, while Wolfram is known for his work in developing Mathematica and Wolfram|Alpha, and for his contributions to cellular automata theory, outl
Everyone is now racing to create open-source alternatives to compete with GPT3.5/GPT4. A common shortcut used by some teams to bootstrap their effort is to fine-tune their model on ChatGPT output. I used to think it was a good idea and totally fair play to do this. Actually, I still think it’s fair play. OpenAI effectively distilled the entire web into its models. They are saying themself that they are using publicly accessible information (mostly). So distilling their model is, in effect, distilling the public open web, so small Term of Service details aside, I don’t see major ethical problems with that. Right? Well, it’s not entirely true and I realized now that, even when ignoring the ethical considerations, using their output is a really bad idea.
First of all, from a purely technical point of view, as @yoavgo is explaining it beautifully in his recent post, there is no way to align LLMs correctly without the RLHF component. I encourag
Twitter thread: https://twitter.com/theshawwn/status/1456925974919004165
Hacker News thread: https://news.ycombinator.com/item?id=29128998
November 6, 2021
jnp.device_put(1)
is deceptively simple to write in JAX. But on a TPU, what actually happens? How does a tensor containing the value 1
actually get onto a TPU?
Turns out, the answer is "C++", and a lot of it.
iperf3
serverwg-quick down wg0
/etc/wireguard/wg0.conf
file// Command iossize predicts the impact | |
// on memory usage of changes to the binary. | |
// | |
// This implementation uses dyldinfo to determine | |
// exactly how much memory the dynamic linker will dirty | |
// as part of launching the executable. | |
// | |
// It is not perfect. There are multiple sources of dirty pages: | |
// | |
// 1. dynamic loader rebase/relocs due to our code |
// This can grow a Robin Hood linear probing hash table near word-at-a-time memcpy speeds. If you're confused why I use 'keys' | |
// to describe the hash values, it's because my favorite perspective on Robin Hood (which I learned from Paul Khuong) | |
// is that it's just a sorted gap array which is MSB bucketed and insertion sorted per chain: | |
// https://pvk.ca/Blog/2019/09/29/a-couple-of-probabilistic-worst-case-bounds-for-robin-hood-linear-probing/ | |
// The more widely known "max displacement" picture of Robin Hood hashing also has strengths since the max displacement | |
// can be stored very compactly. You can see a micro-optimized example of that here for small tables where the max displacement | |
// can fit in 4 bits: Sub-nanosecond Searches Using Vector Instructions, https://www.youtube.com/watch?v=paxIkKBzqBU | |
void grow(Table *table) { | |
u64 exp = 64 - table->shift; | |
// We grow the table downward in place by a factor of 2 (not counting the overflow area at table->end). |
// RCL 05 June 2021 | |
/* | |
verify with `openssl pkey -in <privatekey>` or `openssl pkey -in <privatekey> -pubout` | |
the latter should match the publickey | |
*/ | |
package main | |
import ( |