From the article, it's for "jobs in sectors like agriculture and construction". Would be interesting to learn about how this kind of work is managed in hotter climates.
For office work, a lot of European countries (especially the UK) haven't invested in AC as much as the rest of the world because they haven't needed to. This is especially apparent in housing, where working from home is becoming difficult in these higher temperatures.
It's hard, in my opinion, to lend credence to the author here when they decided to devote the first and largest section of their article to an incisive display of speculative ad hominem.
Would have been a great opportunity to outline the benefits of Zig! I've been keen to pick Zig up recently due to mitchellh's evangelism and inspiring writing on the subject.
481 upvotes on HN, and only $136 USD donated (out of $64k target) -- at the time of writing.
Given the amount of traffic this project has received by being at the top of the front page for half a day, one has to wonder if a different approach to soliciting donations would have yielded them more money.
Clearly, everyone here is at least interested in the idea of a .self domain, and I wager that most (even the naysayers) of the commenters would register theirs.
Imagine if instead of asking for a $15–125 donation behind a CTA, they asked for $2 to "pre-register" your domain (with higher tiers for more benefits). I have a feeling they would have raised a lot more money...
I disagree if your application is networked. Most SaaS is built on RESTful APIs that can be converted trivially into interfaces / contracts for tool use.
The author alludes to it but the defence to this is seemingly insurmountable at the moment because we’re ostensibly operating LLMs on a single channel — their inner, subconscious voice. Right?
Interacting with an LLM is a bit like seeing the output of an Inside Out (the Disney movie) scene. Or it’s a bit like a human brain that we’re providing tool call access and introspection with some kind of advanced neuralink.
But - like the author says - _we know_ our inside voice from the outside world, because we’re embodied.
Is there something we can do here by attempting to bifurcate internal and external systems? Like a conscious and subconscious stream of information on two separate bands?
If the model somehow knew its User was not it because it was clearly an external signal, then the attack documented here would be about as effective as a Jedi mind trick without the Force.
I think something that is a mix between localStorage or IndexedDB and access to the user's filesystem would be better.
I agree with the comments about how much of a security risk this poses. But, isn't that the case with any binary or executable files and apps we download from the internet anyway?
It would be cool if you could have a specially-demarcated directory (e.g. even inside the application like `~/Applications/Chrome/<website>/local_files`) which you can just open super easily with a button from Chrome, and just copy files over into that directory as needed. Would provide the benefits of a more secure enclave with the flexibility of being on the filesystem.
My friend and I have been working on a game: Dozenal. It’s a number puzzle game (with daily challenges) where you have to combine different mathematical operations to fill a grid with “12”s.
I'm beginning to wonder how much of a useful metric the pelican is because surely the frontier labs must be training their models on pelican-artistry because of how well known your test is now?
I agree with the author that -- right now -- we're still in the part of the AI adoption / product development curve that it's an extreme force multiplier.
I like to think of it as a normal distribution, the further away a programmer is to the right of the mean, the more their benefit. It's almost like it's their standard deviation squared (σ²). So someone like Matt Perry (as OP mentioned), who is a >99.99% programmer for argument's sake and is therefore four standard deviations away from the mean... Matt gets a (4×4) 16x multiplying effect on their productivity.
Someone who is a slightly above average programmer might see a 2 or 3x boost on their productivity, which is huge(!) and might also make them fear for their job. Which tracks with the level of moral panic we are seeing and experiencing. This math kinda still holds up for "bad programmers" too (i.e. left of the mean), as in they still see a boost to their productivity (negative squared is a positive number)... but there's something iffy about their results. The technical debt is unmaintainable and because they don't _understand_ the systems that they're operating in, they end up in the "3 hour" prompt loops that the OP refers to.
> Similarly, if Matt Perry handed me the keys to the Motion repository and told me to take over, I wouldn’t have the same results even though I have access to the same set of LLM tools.
The question is -- how long is this multiplier going to exist for? Some people would wager "for the foreseeable long-term future"; some people think it will widen further; and some people think it will diminish or god forbid even collapse. It feels like most arguments at the moment (like this article's) are that the humans who "know what they are doing" will be able to baton the hatches and avoid being usurped by ever-capable models. I saw it in a café yesterday: someone was using a coding agent to build a marketing website for their project, getting more and more frustrated by not getting the outcome they wanted. Their friend typed a couple of sentences on their keyboard and got a "Dude! How did you do that? That was sick!" a minute or so later. "I used to build websites" the friend said. -- The friend 'knew what they were doing'.
How much longer is knowing what you're doing going to be a moat?
I think this is one of the key takes right now. I too have similar experience.
Which way is it going to go?
i) “Seniors” also get superseded by even more capable models that can do all of the things which currently require experience.
ii) Linguistics become the new higher order abstraction (English is the new high-level programming language) _but_ there are different / orthogonal ways of approaching software development than the way we do things now — which “juniors” become more adept at more quickly.
It is a pity that you can't make an experimental commit on an experimental branch without igniting a fire of delirium through some people who -- if they were able to put their emotional response aside for a minute and could weigh this up on the basis of merit -- would probably agree with the motivations for researching this approach.
> if/how hard it’d be to get it to pass Bun’s test suite and be maintainable
Every month brings new opportunities to completely abstract the process of porting code with agents, all using linguistics. What an exciting time.
For those looking for a similarly interesting (and interestingly similar) example, see Cloudflare's port of Next.js[0], "vinext", from a couple of months ago. It had some teething problems at the start but I'm using it in a few production projects now with minimal issues.
I've been working on an adjacent problem (extracting website branding data from a URL) for the past year, and previously had to rely on procedural techniques such as these -- props to the author!
However, models are now getting to the point where we are starting to learn the bitter lesson[0] even with stuff like color-palette generation. Nano Banana 2 [gemini-3.1-flash-image-preview] especially is adept at performing arbitrary operations on images. Before then, you would have to use a model such as Gemini Flash to perform segmentation[1] and then post-analyze those segments.
Here's a prompt I used with Nano Banana 2 in AI Studio
> Derive a coherent, designer's color palette from this image alone.
> Provide 5 distinct HEX color codes as your response.
[Attachment == the picture of the car, first in the author's article]
[Settings: Output .. images & text; Thinking level .. minimal]
Response:
> I have extracted five distinct hex color codes directly from the key elements in this image, representing the colorful facade and the vintage car:
> #FF96C5 (The main pink wall)
> #38C6F1 (The light blue car)
> #AEF6A5 (The green wall)
> #E51988 (The dark pink trim and railing)
> #5F432B (The dark wood of the door and windows)
And they all pretty-much check out. Not hyper-accurate, but really not far off anymore. I didn't even have to try!
Today, my focus is on personalizing the internet at Kenobi.ai (YC W22)
Reach me at my name (Rory) and my company’s domain.