Love it. Especially the random interval. Wondering if anyone has ever proposed doing this whenever you get a text or social media alert. Seems ridiculous I guess but why not?
HN user
pkdpic
art hippie / computer tickler
Ask AI for an initial version and then refactor it to match your expectations.
Write the initial version yourself and ask AI to review and improve it.
Write the critical parts and ask AI to do the rest.
Write an outline of the code and ask AI to fill the missing parts.
So well put. I'm writing these on a post it note and putting it above my monitor. I held off on using agents to generate code for a long time and finally was forced to really make use of them and this is so in line with my experience.
My biggest surprises have been how much the model doesn't seem to matter (?) when I'm making the prompts appropriately narrow. Also surprised at how hard it is to pair program in something like cursor. If your prompting is even slightly off it seems like it can go from 10xing a build process to making it a complete waste of time with nothing to show but spaghetti code at the end.
Anyway long live the revolution, glad this was so technically on point and not just a no-ai rant (love those too tho).
This is like a masterclass in game design, mobile UI, wasm, character design, game dialogue and interactive paychogeography. I'm gonna show this to my kid's computer club next week. Really fantastic, bravo. Is this seriously a solo developer project??
If anyone knows of similar games / apps / software tools that I could show as examples of solo developer small scope simple UI games I'm always trying to find more..
It's so cool to see this pop up on Hacker News. And also a very cool / smart-seeming trend that could maybe play a role in a more utopian atomized art world. Whatever that means?
My favorite classic suggestion down this rabbit hole that they probably mention (pay walled) is Francis Bacon's full-insano-mode preserved studio. I didn't really get his work until I saw his studio. Fun fact they literally used a painting of his to design the chest-burster in Alien? (I just learned that somehow)
https://www.francis-bacon.com/artworks/studio
http://alienexplorations.blogspot.com/2015/02/ridley-inspire...
Read about it on HN first clap-emoji Bravo to the dev / devs who made it nicely done!
Beautiful documentation and seems like an ambitious productive journey so far.
I might have missed it but would be very curious to know more about what field the writer was / is currently working in and what a potential career switch into tech looks like right now. I transitioned to coding after almost 10 years teaching but that was before the glorious AI revolution began.
Seems like the break-into-tech narrative has changed drastically. Maybe not though, curious what others perceptions are.
I agree with both comments here. I wonder what the plausibility of fully autonomous trucking is in the next 10-30 years...
Is there any saying that exists about overestimating stuff in the near term and long term but underestimating stuff in the midterm? Ie flying car dreams in the 50s etc.
For anybody into prehistoric abstract symbols who hasn't encountered this, "The Signs of All Times 1988" [1] is a super interesting study. Also very readable for the majority of us who are not in the field. Pairs nicely with Herzog's Cave of Forgotten Dreams [2] and any mid-tier Cabernet.
[1] https://www.jstor.org/stable/2743395
[2] https://en.m.wikipedia.org/wiki/Cave_of_Forgotten_Dreams
And just my two cents as an under-qualified former art history teacher...
It's fascinating and totally valid to try to analyze these symbols as proto-linguistic, but it can be even more interesting to imagine the cognitive roll these kinda of abstract symbols might have played outside the scope of language as we understand it.
Trying to imaging the structure of the mind and experiencing reality with a complete absence of language can be immensely mind-expanding, even just as a thought experiment. At least it was for me.
I have been waiting for this for a long time. Very happy to see this thank you to the dev / devs! hands-emoji
this is beautiful, the video with the two guys in the urban landscape was especially inspiring, looking forward to experimenting with this someday
Each case is different, but many voice the same laments: Overheads are killing businesses. Sales are down. It’s no longer fun. Primary pricing is untenable. Major collectors have stopped buying art or significantly reduced their spending. The next generation isn’t there to take over from the old guard. The art world has become bloated, and there isn’t an easy way to cure the malaise.
“I don’t believe for one second that it’s cyclical,” Belgian collector and art market commentator Alain Servais told me. “It’s structural. The infrastructure is too big. There are too many advisors, too many galleries, too many artists, too many fairs. Everything will need to downsize. In my blunt opinion, blood will flow in the streets before the art market finds a new balance.”
Super exciting to imagine what new structures and ways of making and sharing art might arise in the aftermath of this system. It seems like in a lot of ways the gallery / collector relationship is still running essentially the same way that was established in the 1870s.
Love this resource, really looking forward to perusing the full text.
And to echo what others are saying I have spent the last month experiencing for the first time how not simple throwing a meaningful test suite together is for a ginormous legacy codebase. I was glad the author briefly seemed to acknowledge that but still... the pain...
They said the playwright ui was supposed to make it easy... Just plug it into an LLM they said... It should just take a few days right?
Just want to point out this felt like the absolute perfect length for a blog post. Very inline with what was being communicated.
I just want to say this is an amazing resource and I'm planning to share it with my 5yo son's computer club. Would be super interested if anyone has any similar resources.
I just want to say that this is fantastic and I'm planning to show it to my 5yo son's computer club.
My impression was that the author was referring to *self-amplifying like a positive feedback loop.
I agree I would have loved more of a hard / concrete definition oriented approach to the whole piece but everything they were saying really resonated at least in terms of my personal experience. I haven't ever come across a writer focusing on this. It was really unexpected / refreshing. It's already is reshaping little moments in my day like hugging my son just now. Very unexpected transcendental value for an HN skim while ignoring a boring zoom standup. The truth is out there.
Somebody could probably throw out the probability of those two 10,000 sets overlapping. Not me though, unless it's 10,000^2...
Agreed, sometimes it seems like there are only two types of roles. Maintaining / updating hot mess legacy code bases for an established company or work 100 hours a week building a new hot mess code base for a startup. Obviously oversimplifying but just my very limited experience scoping out postings and talking to people about current jobs.
Regardless this just made me shudder thinking about the weird little ocean of (now maybe dwindling) random underpaid contract jobs for a few hours a month maintaining ancient Wordpress sites...
Surely that can't be our fate...
Congratulations on #2! (and #1) You're right I think, I share the belief that the new arrivals will remedy the city council / zoning / housing stagnation issues one new development at a time. I'll miss what the Sunset was but a few new condos along 19th etc will make it feel a lot modern.
Glad to see this pop-up. For whatever it's worth I was born in the Sunset (SF) and love the city in spite of all it's problems. My parents were forced out when I got a school on Treasure Island for my 1st grade lottery pick. Went back to SF for college, east coast for grad school where I met my wife from Milwaukee. We have a 5 year old now and I would love to move back to SF and raise my son there. But no matter how many different ways I try to analyze it I just can't come close to justifying the move as beneficial for him or for our marriage. I'd have to work a more intense job to make enough to afford even a quarter of the space we have now. And without knowing our lottery pick in advance I'd have to budget in private school for at least twice the price we're paying for our current STEM-focused private option.
I don't have any personal aversion to working more to pay for more expensive options but the tradeoff of time keeping my relationship with my kid and my marriage healthy is hard to ignore and seems like a really concrete deal-breaker.
We're at the edge of Land Park in Sacramento where my extended family is from. We thought it might be temporary before getting pulled back to the bay for work or schools maybe but the culture here has just been so positive and conducive to family. The public and private schools are excellent with dozens of options, everything is bikable and green, there are literally more museums and restaurants than we can keep up with and the parks / sports options for kids are amazing. And it's swarming with healthy young working / middle class families about half of which are bay area expats. The city obviously has some known issues but I'm continually grateful with the amount of new development going up in every direction and the overall feeling of being a culture / city that supports young cool people having families.
Anyway I'm just surprised and disappointed at how hard it is to justify moving to SF right now as a native who loves it there. Even as someone working in tech / AI with a strong desire to go back. If you have a family, it just seems impossible to make SF make sense right now. I could be missing something of course.
Curious what other SF or Sac tech parents have to say about all this. So much of this has had to be hypothetical on my end because I know so few parents with young kids in SF...
Yeah in a perfect world I absolutely agree. But the reality I'm observing is that everything continues to always be behind schedule (not a new phenomena) and if anything expectations from project leads / management are just getting less realistic leaving Jr devs in even more of a position of "no time to be curious or learn deeply just get it done" and teamleads reviewing PRs in a maybe even worse position of "no time to get into a deep review / mentorship session just figure out if it breaks anything or not". And ultimately clients are still just living in fantasy land in terms of expectations both in terms of build out time for basic features / patches and also how much AI razzle-dazzle they expect for new project proposals.
Nothing can move fast enough to keep up with these hype-fueled TED talk expectations all the way up the chain.
I don't know if there's any solution and I'm sure it's not like this everywhere but I'm also sure I'm not alone. At this point I'm just trying to keep my feet wet on "AI" related projects until the hype dust settles so I can reassess what this industry even is anymore. Maybe it's not too late to get a single subject credential and go teach math or finger painting or something.
I wish I had had this 5 years ago. The early laptops are worth scrolling down for. Really amazing resource.
Anybody aware of similar resources for other early computer patents for Apple, Commodore, Tandy etc? Or another IBM resource specifically covering more than just keyboards ie the 5150, PC Jr etc?
Perfect length post, perfect CSS, perfect font family.
For whatever it's worth after years of being in a space that felt very similar to this my solution was... Having a kid and / or going to Recurse Center and / or moving to a non-LA/NY city.
I don't know if any of it's causal but I have finally crossed over some kind of line. I read books again (like I ever really did), I don't think about social media, I don't have that toxic icky parasocial relationship feeling, I don't even know how to use social media UIs when I see them anymore.
Its fantastic, I'm sure writing / reading this kind of post is a good first step so bravo and welcome (back) to the resistance.
Wait does HN count as social media? Does linkedin? Does Slack ir Teams at work? Does SMS??
Absolutely perfect blog post. You provoked some new thoughts, convinced me of your position, taught me something concrete and practical about debating, had a human narrative, gave me a good book recommendation, didn't feel manipulative or formulaic, wrote something that an employed person can read in a reasonable amount of time AND most importantly made a solid Matrix reference.
You're my blog hero, thank you for being cool and setting a good example. Also really important LLM hype reminder.
From that article:
KEY POINTS
The U.S. Department of Defense on Monday said it's granting contract awards of up to $200 million to several AI companies.
The DoD's Chief Digital and Artificial Intelligence Office said the awards will help the agency accelerate its adoption of AI solutions.
The recipients of the contract awards include Anthropic, Google, OpenAI and xAI.
[https://www.cnbc.com/amp/2025/07/14/anthropic-google-openai-...]
you and me both brother
Omg so glad you saw the post! Thank you for responding and thank you for that amazing space it was such an inspiring visit! Didn't realize there were more Recursers in the mix over there but of course that makes sense.
I'm likely going to be switching into gear with the physical space towards the end of September but I'll try to find you on Zulip and say hello before then : )
Oh man I'm swamped till the end of September but we should grab coffee somehow if ur still in Sac... Although it's possible we've already crossed paths.
That's a really refreshing articulation. Like participation in a multitude of limited-scope benevolent mini-dictatorships. Overlaps with some unexpected conclusions Abundance seems to be hinting loudly at...
Nice, yes I'm such a huge fan of those library-run maker spaces. We need hundreds more imho.