I think it’s complementary - superpowers seems more about what is being told to the agent.
The guardrails outside the agent guarantee it’ll behave a certain way. Still lets the agent write code but makes sure it also writes tests, and prevents boneheaded mistakes I was always telling it not to make.
This traffic guided on-demand build thing, can it be powered by a file which has a standard format?
That’d make it vendor-independent - any vendor could create tooling to generate the traffic file, and you could opt to fetch it at build time or check it into your repo.
While you are technically correct, since any triangle is a simplex, this is not relevant to this visualization.
For this visualization: get positive quantities in 3D space, normalize to 1, now you have dot on a triangle on 1-sphere in a positive octant. Project triangle into 2D space a this is your visualization.
Everyone needs to quit trying to one-shot, and quit assuming AI can’t do it because it can’t one-shot it.
Since the author can enumerate the problems and describe them, it’d be interesting to just use the one-shot pickleball racket model as a starting point. Generate it, look at the problems, then ask an agent to build “fixers” for each problem - small scripts (that they don’t need to build themselves!) which address each problem in turn. Then send the first pass AI output through a pipeline of fix scripts to get something far better but not quite there - and do final human tuneups on the result.
That’s not really how 3D modelling works. You can’t just improve some of the model. You have to improve all of it. Fixing to top of the paddle also changes how the junction at the handle goes and so on. That’s why no one has solved ai 3D modelling yet. It’s like asking a gymnast to learn how to do the second half of a handspring first, and then for step 2 they can learn the first half. It doesn’t work like that.
But if you already know how to 3D model manually, like the author does, why would you spend all that time trying to fix the AI output? For users capable of creating such outputs themselves, the time saving is the point.
If you don’t know how to do it manually then of course that time is well worth it.
It’s about getting to 90% more quickly and getting the job done at 80-90% quality in less time. Potentially an order of magnitude less. If you can do that you can do it again and end up making way more stuff and hopefully more money.
There’ll always be people you can buy handcrafted goods from, who swaeat over every detail. In fact that is my preference when I can afford it - but often I just need a job done so I’ll buy whatever is cheapest and gets the job done.
With AI what’s emerging is a category of “good enough, but way cheaper” products thanks to this mix of AI generated, then human-polished work.
It’s the same idea as using a video editing tool to splice together a bunch of AI videos into an ad, having never gone on site. And it’s quite often exactly what’s needed.
A motivated entity publishing a bombastic opinion. Hard to know what to make of this. If you believe claims about an economy they have a vested interest in affecting, better be sure they’re trustworthy.
These opinions masquerading as statistics is why governments create departments to publish trustworthy statistics.
This is a beautiful example of a little prompt engineering going a long way
I asked Gemini and it got it wrong, then on a fresh chat I asked it again but this time asked it to use symbolic reasoning to decide.
And it got it!
The same applies to asking models to solve problems by scripting or writing code. Models won’t use techniques they know about unprompted - even when it’ll result in far better outcomes. Current models don’t realise when these methods are appropriate, you still have to guide them.
Could be, if you can set up a millions of dollars regulatory apparatus to keep online some really old MMOs for the 100 people worldwide who want to play them, there's really nothing you can't regulate.
This is a common mischaracterization of stop killing games. It does not propose publishers keep games online indefinitely, but to provide the bare minimum to the community to host them if they decide to shut the servers down for good. If the 16-year-old Unturned dev could do it, so can AAA studios
They're pretty up front about the fact that the final result is going to have be some sort of compromise.
Based on the words of the most involved proponents of the movement have said, the absolute least they could be forced into accepting would be "Developers can't sue people hosting reverse engineered servers after the main game has gone offline". Which is trivial to comply with (just don't sue someone), but probably insufficient for living up to the main messaging of the movement (since there's a lot more games that people care about preserving than games people care enough about preserving to completely re-implement servers for).
Slightly more reasonably, there's the pitch of "release your server binaries". As the market stands at the moment, that'd be difficult, because in large studios it's common to have all sorts of licensed software involved in hosting your backend, but it's the kind of thing that's pretty trivially responded to on new projects: companies selling software for game service backends would have to adjust their licenses in response to their customers' legal requirements, but that's far from impossible given all the licensed code that's running on client machines already.
In the best possible world, consumers would get access to the source code of the entire project after the company is done making money on it, but everyone involved seems to think that's a pipe dream.
If only it would actually work that easy for democracy(people's will) to control the actual important things of society that fuck us, like housing, money printing, immigration, tax % and where that money goes to, healthcare, foreign aid, jailing epstein clients, etc.
They’ll teach us what we need to know to create something that will do what they’re trying to do.
reply