plaguuuuuu

Yep it's all AI-generated. It's annoying that they have a fake human as the author but whatever, it's the interslop.

There's this one guy doing crazy stuff with ASCII rendering, I can't remember his name/handle/project though :(

I'd much rather spend $10 than have to sit at a prompt every day babysitting the thing, after working all day sitting at a prompt babysitting other things

How do you keep the info the AI generates concise?

I'm grappling with this at the moment, getting it to do design or reverse engineering work, during investigation it makes the wall of text bigger rather than consolidating. It can never pause and create abstractions properly. This is on Opus which starts getting wordy and performative on goals it can't easily verify.

Can't help laughing at a random ad hominem against John Carmack of all people, and about his opinion on a guy who is already widely regarded as an especially talented programmer.

That's exactly what Fable is. They use Fable to improve Fable. I reckon the successful experiments must go into the model training set with a strong RL signal, and that is why they are so paranoid about people using Fable for LLM tasks. Fable knows what it did to improve itself. Pure speculation of course.

No offense but if you haven't done enough research to actually have a studied opinion, maaaaybe you should avoid posting an inane comment about it.

Also worth reading, especially today in LLM age: Simulacra and Simulation by Beaudrillard. Heavily inspired The Matrix. Although unlike the movie, he saw simulacra as irreversibly replacing reality, ie you can't get out of the matrix.

you could try

* googling "CTF security"

* asking literally any AI to explain the article

Yes, you must beg. If you don't know what a CTF is, and don't want to find out, why read the article anyway

I don't think it's that hard to get them to say "I don't know"

I'm pretty sure they are actively trained to avoid it.

Besides, like, what would you do if you asked your $200/mo AI something and it blanked on you?

Instead of doing creative work on the iPad, it should really be used as an input device for the mac.

"Coding style should reflect the casual minimalism of expert programmers" used to to bump it up a bit, I guess it had the right activations or whatever, but I haven't bothered as much with this stuff with recent models cause (a) writing "You are a gigachad developer who is a Level 99 Staff Wizard at FAANG" doesn't work any more and (b) More or less they code like what they can see in their context; if you have a shit codebase you're going to get more shit, so theoretically I'd give a baseline coding style in some instructions, but realistically I haven't have enough motivation to bother with the last thingy I was working on.

I've recently had the interesting experience of working on a Clean Architecture project for the first time. Pre and post-LLM adoption.

It has been... difficult. Services/modules organised by infrastructural layer rather than by feature. A mediator pattern abstracted away the handling of commands. Just in case one day you needed CreateFooCommand to be executed by a different handler, or something, I dunno. It was so hard to figure out how to navigate everything. And it felt like the entire tradeoff was for the purpose of stopping smoothbrains from adding the ORM to an API endpoint - but with the cost of this crushing accidental complexity that made it hard for everyone to hold everything in their heads, not just for me but also for the smart guys on the team.

It turns out that the LLMs also performed extremely poorly. All the heavy abstractions were too hard for them (not to mention most of the developers).

I knew I had no chance of shifting things away from that paradigm. But as luck would have it... we started basically vibe-rewriting it from scratch without bullshit enterprisey crap and its (a) dead simple (b) has most of the features after one month (c) even though the code is questionable, inelegant AI slop, with nearly zero regard to proper architectural design, it's way easier to deal with than before

I've never felt so vindicated.

I'll carry an ammo belt of little EMP devices.

im pretty sure gastown (the Beads part) stores tasks/memories/whatever in a DAG but I haven't looked into it in detail

I've always held the view that successfully using AI requires more knowledge and skill, as the burst radius of poor engineering decisions or lack of domain knowledge is way larger.

I just cannot see WITCH doing this without exponentiating the usual problems with outsourcing. I've seen some horrors. Can't wait for contractors wielding unprecedented chaos.

no way, I didn't realise this worked.

My attention span is such that I get side tracked and wind up taking longer than 5 mins quite a bit :D

I'm only 50/50 but I swear they have only one app for the entire globe.

Can you imagine how complex that must be vs just making like 100 different apps in each country.

But eCoNoMiEs oF sCaLe

If you're balking at makin 100 different apps, then for reference, I am pretty sure my local mcdonalds - just the one restaurant turns over >10 mill a year, so you get a sense of how much they'd want to invest in, idk, the ordering front-end of every maccas in Australia

or sticky-tape it to the window.

d5 has an actual shutter yeah? not mirrorless? I think the shutter moving will spin the camera.

guarantee one of them caught an OpenAI guy murdering a prostitute or something

what do you even do on X, you basically just subscribe to a bunch of blowhards to get insider sloppy seconds, then occasionally yell into the void and hope someone (anyone) finally responds?

too labor intensive - each launch already costs like $1bn, how bad can it be

I don't think a popular audience is buying a book on mathematics.

But, the world is huge. Even if this is kind of niche (people who didn't really get into maths in school or college, but now have a strange impulse to pick it up for shits and giggles) the audience is still thousands of people. Or just, people who want to see how Tao connects everything up, because the way he sees and explains stuff is amazing.

There are levels to what's worth publishing or working on in general. Hardly anyone is going to be the next Steven Hawking but this obsession with the most popular or successful celebrity creators ultimately leads to this highly homogenised global media landscape. The most exciting thing about the internet for me was always accessing the long tail of truly unusual shit that you wouldn't find in book/record stores, tv, etc.

the "you might also like" for a given artist is usually the most generic related artists - for anything remotely related you'll get basically the same list which is the middle of the venn diagram of everyone who listens to them

even if you limit to 2/3 I think any sort of persistence that can be picked up by agents with the other 1 can lead to compromise, like a stored XSS.

At work we use Clean Architecture which is incredibly hard to browse, even though I've been there for 6+ months now and know where everything is, I have to use so much working memory to gather together the files for a feature slice (endpoint, command, command handler, etc).

I've thought for a while of building this exact thing as a vscode extension because of how utterly shit it is :D

I really want the source code!

Think of the lengthy prompt as being like a safe combination, if you turn all the dials in juuust the right way, then the model's context reaches an internal state that biases it towards different outputs.

I don't know how well this specific prompt works - I don't see benchmarks - but prompting is a black art, so I wouldn't be surprised at all if it excels more than a blank slate in some specific category of tasks.

good luck doing anything if kafka is down though

Could one put the DLQ messages on a queue and have a consumer ingest into pg?

(The queue probably isnt down if you've just pulled a message off it)

teams works fine in website form for me because it IS a website (that uses an extra ~1gb of ram running as a desktop app because its also a separate browser)