I think this is one of the more concise tellings of how to think about where the current LLM-based crop of AI models can be useful in a product:
There is something of a trend for people (often drawing parallels with crypto and NFTs) to presume that [incorrect answers] means these things are useless. That is a misunderstanding. Rather, a useful way to think about generative AI models is that they are extremely good at telling you what a good answer to a question like [the one you asked] would probably look like. There are some use-cases where ‘looks like a good answer’ is exactly what you want, and there are some where ‘roughly right’ is ‘precisely wrong’.
– Building AI products — Benedict Evans
So, the question to ask when looking for a good product fit: is the upside from shortening the time it takes to get something that looks right (and can be fixed up) greater than the downside of inaccuracy or downright falsehoods?
Some other recommended reading from the same author:
Apple intelligence and AI maximalism — Benedict Evans
But meanwhile, if you step back from the demos and screenshots and look at what Apple is really trying to do, Apple is pointing to most of the key questions and points of leverage in generative AI, and proposing a thesis for how this is going to work that looks very different to all the hype and evangelism.
Looking for AI use-cases — Benedict Evans
We’ve had ChatGPT for 18 months, but what’s it for? What are the use-cases? Why isn’t it useful for everyone, right now? Do Large Language Models become universal tools that can do ‘any’ task, or do we wrap them in single-purpose apps, and build thousands of new companies around that?
I have used SSH as a way to get a shell on a remote machine for over twenty years, but I’ve never given that much thought to how the protocol works. In retrospect, I find this a little surprising as I tend to love this stuff.
But I got a chance to dig into it at work recently. In doing so, I found that my remote shells used a significantly more sophisticated protocol than I imagined. Instead of being super-specific, SSH turns out to be a general purpose, multiplexing, secure connection protocol, whose killer app appears to have been remote shells. I wanted to write a bit about it, to cement my understanding and give an introduction to the power SSH has.
The aim of this post is to give a working understanding of how SSH works one level down from how we typically see it. We’ll not cover the setting up of the SSH connection, but we will cover how the SSH client asks the server to do things like open a shell or run a program, and how data is moved between the two.
Go has an SSH client and server in its extended standard library,
golang.org/x/crypto/ssh. We can
use this to explore the SSH protocol in more detail. We’ll do that by building a
simple SSH server that can run a single command, like when we run
ssh mike@myserver.com ls -l / — ie, run ls in the root directory on the
remote server. As we are doing this, we will log activity around SSH’s
underlying primitives to peek under the covers.
Since my last post, I’ve committed a couple of updates to toykv. The first is a nice functionality update, the second is enabled by my learning a little more rust.
Implement delete · mikerhodes/toykv@2325ff1
With this update, toykv gains a delete(key) method. I did this in
essentiallly the way I outlined previously: by adding a KVValue enum that
holds either a value or Deleted, then threading this through the library,
including serialisation.
Use generics with Into<Vec
This is a nice update that reduces the amount of boilerplate, especially in tests.
Previously there was quite a bit of get("foo".as_bytes().to_vec()) code,
which has now been reduced to get("foo") by making the get, set and delete
methods generic.
I think this can further be improved using Cow. I think that would
avoid unneeded cloning of data. But that is for later.
Obviously the library is still a learning aide, but it’s getting closer to at least having the functionality you would want in a real storage layer.
In the early part of my experiments in writing a very simple document database, I thought that writing the bits to disk would be too difficult for me. And perhaps it was, back then. But I think things have changed.
As I wrote more of the document database, I got more experience transforming JSON data into key and value byte arrays that could be saved, retrieved and indexed. And as I got more comfortable with the tiny data formats I was creating, particularly for the indexes, I began to think, “why not, I bet I could write the code that organises these on disk too”.
Of course, just as my document database is nothing like ElasticSearch, my on disk formats would be nothing like so advanced as sled, the key-value storage layer I was using in my document database.
(I still think that I’d need a bunch more practice in this space to be able to write something production ready; but I am starting to think that I need not be a Better Programmer, but instead merely More Experienced In This Subject. Perhaps, in the end, they mean the same thing).
But I thought it would have a lot of value, to me at least. Because I believed I’d learn a lot, even writing the simplest, silliest key-value storage engine. And I think I have, and to try to cement that knowledge into my head, I’m going to write a whistlestop tour of that code into this post.
ToyKV now has code and structure that is almost tidy enough to write some more about.
In the meantime, I found this deep dive into some of the architecture designs of S3’s new low-latency storage a good read:
Recently, Amazon released their S3 Express One Zone Storage Class, advertised as the “fastest cloud object storage for performance-critical applications.” In this post, I’ll highlight three key features of Express One and share some guesses regarding their implications on S3’s internal architecture.