hollowturtle

In my experience they're never blind they can't even explain why they chose a more verbose, unreadable and error prone approach instead of a simpler one, only to candidaly admit that "you're absolutely right!". You can improve the observability how much you want, it will never prevent agents to go off the rails and destroy the database

Makes me smile, seems ai written too. Agents will never fix this mess, it's upon us. But not in the way you're thinking. Asking agents to fix the mess they've been trained on, that they work on and they're made of it's just blindness utopia. We "just" need to part ways with current platforms(talking to you web) and build better abstractions and paradigms. The web plarform as is can't be saved anymore especially from us. It says a lot that many people get excited for a damn dialog html feature that we needed 20 years ago and it's also uncomplete

We're out of training data, they need to get fresh data somewhere

Show don't tell

Like I said on a comment above I think you're wrong because:

> Human slop is slow and easy to contain and build containments around it. Generative AI is so fast that it breaks every possible containment strategy

> Most of human-generated popular music is slop

I think all these laws/theories etc needs an adjustment to today's reality. Human slop is slow and easy to contain and build containments around it. Generative AI is so fast that it breaks every possible containment strategy

Wow that was fast

No, I expect it from him and from an Anthropic employee to brag about not even reading the code, so I can't be interested more. Also coming from personal experience, I spend tons of hours a week cleaning up AI generated shit from the latest and hottest and more expensive model currently existing. It's impossible he doesn't read or tweak it anymore, it would not be very functional (or by now someone would already have hacked him)

> I don't actually do anything resembling traditional engineering anymore (read/write code, run commands in a terminal, or etc.), I only talk to Claude and have it do everything.

What values it holds if he candidaly admits of not caring at all at what he did? If you can't put the effort why should I? Who cares

AI in its current form, it's not a tool, it's a product you pay a subscription for

I hope Digital Minimalism doesn't mean depending on an AI product subscription, his written code(which is not minimal) or having a black hole of npm dependencies for running a wallet on the cli that(reporting what's on their repo): "NOTICE: this CLI has NOT BEEN AUDITED and IS UNDER ACTIVE DEVELOPMENT and HAS BEEN WRITTEN WITH HELP FROM CLAUDE et al"

What a "fantastic" era we're entering into. I think eventually these people will have a minimalistic life, with malware stealing everything

Totally agree but I suspect that our desires are in contrast with ai companies profits

LLMs. This month has been very busy

How we've ended up cornered in this spot as an industry? From human craft to onboarding and baby sitting agents?? That sounds just stupid. I won't be surprise to learn, after ai companies go public, that those who pushed hard for agentic coding just disappear o will push for something else. What we have produced so far of extraordinary or even just good value? Please no math conjectures or advancements, there is no field benefit in brute forcing problems

> Though I think a far more interesting thing would be whether AI given the corpus of 19th century mathematics and physics reproduce what Ramanujam or what Einstein did.

I don't think so, it was a big leap forward in terms of creativity, imagination, rigor and experimentation. Einstein was able to "run" visual thought experiments inside his mind

I have the same theory but for different reasons(commented something similar to a recent css functions thread), in this case though I don't thing you can solve it with a library, the canvas api is very limited, text layouting is very hard especially if you want to support different languages and directions. Let alone rendering a text input, if the use case is games, those usually don't have very complex inputs and that would be ok I think to implement a simpler one. IMO we should just have exposed the Skia text layout api in javascript.

Gosh how much I'd love to have a separate accessibility and text layout api like skia has and ditch the dom completely

> Because those making the standards only work on creating gimmicks.

Totally agree, but afaik we are a very small minority. My tinfoil hat theory is that all of this is intentional to keep monopolies and making it impossible to compete in the browser space

> typescript added human readability

Ehm no, added type safety, and dealing with a type checker it's exactly what agents need.

> if no human is coding

Nope outside the bubble there are many still hand coding(me too)

> I guess it will be soon that typescript won’t matter anymore since agents will be writing code is Rust

Oh hold on a second isn't Rust the same as Typescript "adding human readability"?! Why not trashing Rust and just have LLMs output WASM directly? XD Wasm which is basically useless outside the browser or some microvms on the edge, and in the browser you don't even have an interface for directly rendering anything and still have to deal with the dom

You either are highly non technical, very junior or I just don't know

All of this just for enabling the WASM use case? Why not keep supporting Deno then that is written in Rust? To me it just sounds like a technical ai journey and a blow to the go port

Then you have a skill issue :)

> Especially early-stage businesses where time to market and test ideas is paramount

To me it's just crazy of how dumb it is to test an idea with a vibecoded shitty app. I'm not saying it should be perfect from day zero, let's pretend we are talking about cakes, how crazy it would sound you will tell people to try and judge your new idea of a cake you don't even know how it taste or what's inside?

> We've vibecoded scripts recently that genuinely are better than what I would have written and I don't think I'm terrible.

I'm ok with vibecoding scripts, I love programming the machine and making the end user happy and not dealing with bash! I don't judge scripts quality as long as they are tools in the workflow, I dont care about that, unless they will somehow be part of the production. The name Script implies that, there isn't any architecture and Claude Opus sucks at architecture

Then you're just a stranger in a land of nerds, only knowing about the history of computing you would know that coding isn't only a means to create something but it is everything. Would the Michelangelo statue have been 3D printed hold the same value? The problem is that programming got popular because it paid good salaries

Same not sure for the same reasons, to me it all sounds like a big marketing campaign for AI coding. Everywhere I read I see comments bragging about that the quality of these products output is better than us or it is usually taken for granted. Not my experience so far and I'm on the edge of AI usage

> Yes, at work, where you are paid to produce value for a business, the economics of purely hand-written code have changed

I'd love to genuinely love these blog posts but they are all the same! They're all like "now that machine are better than us $xyzargument". I'm so pissed off when I read so blantant lies like AI "writing code better than me" maybe better than you! But in general it's just a big lie.

> the economics of purely hand-written code have changed

who are you to know? I still hand code and produce a lot of value because I do care and polish everything I do. There are some pieces of the software that I wrote that I never touched again, they work perfectly, no errors no customer complaints

I'm always interested in projects like this. But how do I know this is not AI code? Let me explain, I read a lot AI produced code at work, when chilling on nerdy things I really wish I could read just human crafted code, for pure learning and joy, but as time goes on I've seen myself questioning more and more stuff, code, videos, even books I go check the publication date

> fewer “long T” shaped technical purists

Then we will soon forget how our airplanes works

> the value is not in the code (AI can code better than me at this point), nor even in the software architecture (AI is just getting to the point where it will get better than me)

The lies of this decade. Hopefully we will heal sooner than later

Thanks for the long detailed response I appreciate that.

One point worth mentioning is this:

> This is how I see the future of software is going to be like. Programs will be too complex to evaluate, humans will have forgotten how to write code, and the only way left is something similar to psychology as a "science" that tries to evaluate in a sandbox poking kind of way how software works.

I don't want this, and I'm pretty sure you don't want it too, like no one sane would like to have planes software written in this way. Also since you mentioned psychology I think your vision is a bit too much biased towards sci-fi, it reminds me a lot of blade runner/neuromancer and so on :) I think reality won't be as much spectacularly dystopic as in these novels.

Anyways, tangential, I've been a ui programmer for much of my life(games, web and mobile) any suggestion for where to start in reverse engineering? I have some interest in the matter