Well, for example, in one afternoon, I have a parsing engine to understand, which is 9 pages of code. I thought I knew OCaml, having written a few interpreters in it, but I didn't know the {foo| |foo} multiline string syntax, I didn't know about Printf.ksprintf, I didn't know about Buffer.create, I didn't know about String.escaped, I must have once known about List.exists and List.rev_append and forgotten, I'd never thought of pattern-matching Array.to_list Sys.argv as a way to parse a command line, I didn't know about Sys.file_exists, and now I also have to think about what the parse result should look like and how to use it. And Claude correctly pointed out that the way I had thought about handling things like heredocs (or {foo| |foo} strings) would violate the preconditions for using the Packrat parsing algorithm, and suggested that I use the alternative approach of parameterized productions as in OMeta, which I need to think over.
I think that was the same day I prototyped an approach to using Service Workers from localhost as a platform for persistent mobile apps that don't show up in the app list but also don't rely on the TLS CA system for their security. Which involved learning a lot of stuff about the Service Worker lifecycle and localStorage and IndexedDB that I didn't know before.
I love how well this comment captures the experience of engaging with LLMs as a way to deliberately challenge and expand knowledge.
When I see people worry about LLMs atrophying their mental abilities I assume they haven't thought very hard about ways to lean into using them to expand their mental capabilities.
I have been prototyping some network proxies in a largely "vibe coded" fashion and it has been a mixed experience.
It has definitely accelerated my learning: through the process of writing rigorous plans, I have learned so much about network programming... the intricacies of HTTP2, how to design a fast MITM proxy, performance pitfalls in SSL...
These are things I studiously avoided learning for a decade, now demystified, mostly through Claude patiently rendering many figures and diagrams.
And with Fable, I was able to ship a working Envoy Rust extension in a one-shot.
On the other hand, my grasp on the details is tenuous. Every so often the agent can't progress and I am stuck for ideas, hitting different prompts like they were slot machines. I forget how to solve problems by myself.
I can feel myself becoming supine and dependent on something I know is going to become more expensive, a dependency AI vendors will seek to exploit. It has happened quickly. I do not really consent; it is forced on me by my employer.
One thing I may try this week is typing in all the code myself. With the level of back and forth that I've been happy with so far, Claude Pro seems to only be able to produce about 1000 lines of code a day in two or three five-hour sessions. I can totally type 1000 lines of code in a couple of hours if no problem-solving is needed. So maybe I'll look at Claude's code, switch screens to my editor, and type until I don't know what to type, and repeat.
Obviously there are higher-level design issues that I might not notice while engaging with the code at the byte-by-byte level, but I won't have the embarrassing problem I had a couple of weeks ago where duck.ai wrote me a CPU in Verilog, and after I tested it, I tried to write something in Verilog myself and couldn't even figure out how to write a syntactically correct XOR-gate module. (Verilator's parse errors are not designed as a Verilog tutorial, it turns out.)
This hasn't worked out that well for me. I have to try to do it myself, do something wrong, and ask for an explanation of what i broke. Just typing doesn't leave me with any retention.
Yes! The best part is, at any point they are right there to answer any questions, or to challenge or validate and experiment with any ideas! You can go down fairly deep rabbit holes in either case to understand a topic, and -- unlike any other medium other than a live human expert -- you can hone in only on the areas that matter to you most. Or you can just ask it to do something (as long as it's in the digital realm) and see for yourself what happens.
I always say that since one of the best ways of learning is by doing and given that with LLMs we can do so much so quickly, we are in a golden age of learning for those who really want to learn.
I assume that they don’t have time to do that, and are lamenting the fact that exercising those capabilities is no longer on the critical path to getting paid work done.
I'm guessing you've written a well-thought-out, clearly expressed blog post about this that I would absolutely love to read, if only I knew where it was.
The original Castlevania animated show was good, shame about the Warren Ellis situation. Would have loved to see him write Nocturne as well (which was fun but just had a much weaker script).
One suggestion from David Allen that I always liked--mind you I'm not a David Allen afficionado in general--is that if you can do something in 5 minutes, just do it rather than add it to a to-do list. Mind you, 5 minutes can end up taking a lot longer but I find it useful advice in general.
This is close to the Never Go to Zero idea. Especially for recurring tasks, do the minimum, every time. It is probably less than 5 minutes. It's one push up. Just the warmup or tuning. Boot the machine. Open the file. Either more will follow or you'll stop for some reason. But you never skip or push the thing to some other time because that will just lead to more skipping and usually quitting.
It was a general metaphor but a reference to Windsurf. On the boomerang side, Noam Shazeer went on to do Character AI and came back via acquisition only to leave again to OpenAI.
Am I the only one who thinks the "reverse sear" is like cheating? It takes out all of the skill when you move from the pan to the oven, and I lose all of the fun in learning to be chef.
People are allowed to use tools and non-traditional techniques, even when it feels like cheating. They needn't be chastised for this.
The gestapo isn't going to kick in the door and haul folks away for using reverse-sear and a meat thermometer while they cook a steak in their own kitchen.
(And everyone is free to seek their own kind of masochistic pride, if that behooves them. When a person has better satisfaction [or whatever they get out of it] from doing things the hard way, then that's OK too.)
Pretty hard to be criticizing someone severely if I'm not even speaking to them specifically, don't you think? You're making a mountain out of a mole hill.
I'm entitled to my opinion, which I self-described as a bad hot take.
Sounds like you're the one specifically reprimanding me here? Oops...
How can articles on major news sites have typos this bad up for over a month?
"The crisis in France has claimed dozens of lives, with 40 people drowning while attempting to call off from the heat since June 18"
Call off should be "cool off".
And forgive me if this is a stupid question, but don't nuclear power plants produce enough energy that they could power their own cooling? Why do they have to rely on the free cooling provided by a river?
reply