nathanfig

As a developer I almost got defensive, but I think I feel what you're feeling. Dealing with change is hard. I am a developer who once felt value for knowing these things too. Today I wouldn't even bother opening the developer pane to test CSS changes. Tools that held so much potential to me are now headed for a museum, and it sucks.

I didn't ask about standard representations, but I think the graph representation works well when paired with the discrete moves this maze allows. If we wanted continuous spaces it would probably be harder to play and harder to represent, but maybe more interesting.

Yes, I've exported and self-hosted in the past. I'll sometimes use Sites to mockup something and then I'll download and pass it onto another agent for use in something bigger.

Yeah you have actually picked up on something that the game intentionally does to help the user: If the cheese can be reached by any of the dimensions you are currently on, then it will ensure that dimension is in the subset of dimensions you receive when you go down a dimension.

Otherwise I'd have to introduce some kind of dimension picker. Maybe a fun hardmode.

Yeah if I were to make it harder I would introduce more sparse connections requiring the user to actually understand the layout, right now you can kind of "feel" your way towards the cheese. Most brutal maze would be one with only one possible path and lots of backtracking required.

Maybe I'll do that and post to HN later, didn't expect this much response!

Yeah I think moving up and down dimensions is the best strategy. I find spamming movements in 6D works but only because the paths are dense enough.

I mean, with a Cloudflare API key you can pretty much already do that. But keeping your data straight and putting in the right authentication guards, etc. are all still where the business problems meet technical and the AI is not enough unless the agent is both architect and customer.

Thanks! Yeah I find it helps to jump back down to lower (comprehensible) dimensions, move closer at that level, then jump back up.

I have been using Sites a few months now, really underrated feature IMO. Any time I get a quick app idea I just hand it off to Sites and usually get a working prototype within the hour.

For example, here's a game where you are a mouse hunting for cheese in higher dimensional mazes: https://manifold-six-axis-escape.nathan338932.chatgpt.site/

Idea came to me while at a concert, was ready to play that same night.

I hope open weights continue to gain traction for this reason too.

But injecting information into outputs is a little different than Claude keeping tabs internally. The point is that we do not know what information is being shipped with the fingerprint itself.

Yeah it's entirely possible the answer is: "You don't." But I haven't even seen people attempting to imagine life well-lived. Like with so much technology it's basically an afterthought.

I've been pondering the question: "What does it mean to live well with AI?"

We are certainly scrambling for productivity with "token maxxing" and scrambling for entertainment with AI companions, but I haven't seen many thoughtful takes on how AI might look in a life well-lived.

I think that's a big part of what makes this era so much fun - the interactivity tailored to my capability. I feel like I'm 13 again discovering I can write HTML and feeling that giddy delight when I try something and it just works.

>> I haven’t had great luck with winding it up and setting it loose on a task

Yeah there is real labor involved with trying to set up the right context and explain your goals and ensure it has the right tools, etc. etc. Sometimes the payoff is massive, other times it's like "I could have done this myself faster". It takes time to build an intuition for which is which, and I'm constantly having to tune that heuristic as new models and tools come out.

Yeah, the social problem of "how do we use technology well" persists.

Can you elaborate? I might agree, I'm just curious what you mean.

Yeah in fact I think we are going through some major upheaval in development practices because we haven't yet figured out what constraints to put in our use of AI, and so plastering it everywhere we trip ourselves up. It took a while to figure out that private members were useful and GOTO is harmful despite how tempting it might be.

I think similarly we will find that using AI to take shortcuts around design is mostly harmful, but using it to fulfill interfaces is brilliant. Eventually a set of best practices will evolve.

Because they are already useful for programming and unlikely to get worse!

Sounds a lot like "nothing ever happens"?

Reduced costs does not necessarily equal reduced wages, but I see what you're saying. As others have pointed out, making cameras more accessible made photography more competitive.

It may be in the end that software developers make less money even as more jobs become available.

And worrying. LLMs don't fed themselves, we need people to continue sharing solutions. I've contributed some popular answers on SO myself and am happy that an LLM can use that in its training, but rarely go to SO myself anymore.

I'm finding 2.4% unemployment rate for software developers: https://money.usnews.com/careers/best-jobs/software-develope...

Regardless of the true number, you're right that no amount of reasoning on paper "why" we should be employed matters if the reality is different; which it clearly is for a lot of people. Reality decides in the end.

A more accurate title might have been "Why AI is a reason to become a software developer" - since the topic I discuss is entirely AI and its effects on the field, and there might be entirely non-AI reasons for not going into software.

Yeah, with current-state AI I foresee more such opportunities.

Yes, if you built your career on FrontPage you have probably had a bad time. Many such cases.

That said, even if the specific products like Cursor or ChatGPT are not here in 5 years, I am confident we are not going to collectively dismiss the utility of LLMs.

Really! That could make for some really interesting stories. Fascinating to think of LLMs as a customer acquisition pipeline for developers.

Claude made this point while reviewing my blog for me: the mechanization of farms created a whole lot more specialization of roles. The person editing CAD diagrams of next year's combine harvester may not be a farmer strictly speaking, but farming is still where their livelihood comes from.

Yeah I think the combine-harvester analogy is tempting because it's so easy to visualize how wheat can scale over a big square field and project that visual onto lines of code generated on a big square screen... forgetting that lines-of-code-generated is not inherently useful.

An interesting parallel because there were undoubtedly some people who worried we would lose something important in the craft of instruction-level programming, and almost certainly we have in relative terms. But in absolute numbers I am confident we have more low-level programmers than we did before Fortran.

And if I were to jump into instruction-level programming today I would start by asking an LLM where to begin...

I also remember this! Maybe a subconscious influence

Thanks!