Garlef

even if it's not free the users will get monitized - netflix, windows, amazon, bmw, ...

Not quite the full truth:

In my free time; I'm iterating on programming ideas using coding agents.

For example a testing framework that separates test case definitions from instrumentation...

And the recent post on bento.page sent me down a path exploring different ideas around "X as standalone HTML+JS"...

And I don't care about shipping this; It's just for me.

Baumkuchen

> if it was smart enough

and i think this is exactly the crux;

the really big models need really big datasets

and current gen LLMs get a lot of training data beyond "all books + all of the internet"

the objection is then that producing this additional data would already confound it with pre "virtual cutoff date" knowledge (since the training data probably implies mathematical and SWE concepts that were developed post "virtual cutoff date")

> Bonus points at scale you invent a templating solution. Maybe you use JSX

I think this is an underrated perspective in these discussions.

Maybe that's just language preferences the LLMs proliferate

> I’ve also started to think about replacing any kind of CI in the cloud with local.

Same here.

But maybe the answer is not `local` but "dispatch workload (to wherever) from your CLI"

nah thanks;

my workflow:

- ask not only for a solution to a problem but also for specific code (= tell the agent about your mental model of the codebase)

- ask for small stacked 'PRs/branches' and review/refactor heavily also using the agent (= refine your mental model of the codebase)

Isn't startup culture a bit like bumfights?

Rich people using their financial prowess to subjugate others who are in a much weaker position in order to let them engage in unhinged behavior for their amusement and benefit.

If you grow your own tomatoes, you'll have free tomatoes!

(Doesn't really get you a BLT but hey... at least you'll have saved the world a bit because they're not from the supermarket)

/s

idk ~ it's either a bit thin or i'd expect something more substantial "for the AI era"

... as the kids would say: "weak sauce"

... and it's just a tool to create charts not a "visualization language"

you could probably vibeslop a pipeline from some ad-hoc DSL to excel or pandas or R and get a better integration with your business context

and furthermore, codebases can reach a size where good patterns matter much much faster

(so through this mechanism, the pain of not refactoring becomes apparent more often)

My approach at parsing this:

There's two point in time with two ages each:

M, M0, and A, A0

Then the sentence can be expressed as:

* M = M0 + X and A = A0 + X and (X is the time difference)

* M = 24 and ("Mary is 24")

* M = 2 * A0 and ("Mary is twice as old as Ann was")

* M0 = A ("Mary was as old as Ann is now")

node-RED for PLC programming

There's no sensible barrier here: If you want to have agents work on stuff (data) then there's going to be worms.

> asked it to make some slides and it decided to write its own slide rendering engine

isn't this exactly what a certain kind of real world dev would do?

So: Since this is US centric:

- Is it better/worse than other countries? ... better/worse than "comparable" countries?

- What's the historical trend?

- And in both directions (geographical, historical): How does it relate to the respective diffences in wealth inequality?

Appleseed missing! But maybe it's more solarpunk?

Letting the agent rebase stacked PRs (and create the respective subtasks in jira to begin with) is an incredible time saver

It's been a few years (~ 15) since I read it.

The determinant trick I'm referring to is used in prop 2.4 (in the Version I found via Google).

They use the determinant of the adjugate matrix if I remember correctly... But they just hit the reader with this without any motivation or even naming it.

> then that's a problem with the original question - not the solution itself

I think there's a good counterexample to this:

Atiyah/MacDonald proove the Nullstellensatz ultimately by using some trick involving determinants.

They give a very nice theoretical treatment of the content and context of the theorem. But the proof at one crucial point uses techniques that live conceptually outside of this context: While its possible to see that the argument is sound, it does not give a good explanation of _why_ it's true within the context of the theorem.

(You could of course argue that they did not give enough context ... but that's exactly my point: the trick makes the proof work but hides the explanation)

> a human mathematician would aspire to

Some do. But there's also the notion that a clever trick is a bad explanation.

I think trying to iterate on a "spectral decomposition of your intent" - slowly working on increasinly refined breakdowns of what are the different aspects of your project are - both on the domain- and also the technical level; aka requirements and architecture. And then don't directly iterate on the code but rather regenerate/update the codebase based on the new intent and the old codebase... And a decomposition of the whole thing in terms of optics (open lenses, etc) where the decomposition respects the "spectral decomposition".

From the blog post:

> A ProseMirror 2.0 with an incompatible interface would amount to the same but make it ambiguous what people mean when referring to ProseMirror. Trying to graft stuff on in a backwards-compatible way as an 1.x version would produce a compromised win32-style mess.

From the blog:

> I'm not all that fond of the ProseMirror pun anymore either (it's CodeMirror but for prose, get it?)

So... It's time for someone to create Codegard, i guess?

or just ask an llm

The bad thing about this:

Can you trust future governments to respect "Nulla poena sine lege"?

> If you look longer term, a society that does this will end up a lot poorer than one that doesn't.

Got data to back that up?

(On the serious level, I'm really curious; But on the polemic level I'll call BS - I highly doubt there ever was such a period in any capitalist country ever)

I like it;

But I think there's a middle ground: You can definitely use GenAI to bring yourself to the page.

But that requires effort that goes beyond "draw me a pelican riding a bicycle".

I've used to create abstract art/(or "images that look like abstract art" if you prefer - let's not get distracted by this branch of the discourse) using midjourney: getting the AI to output something worthwhile would usually take me hours of iterating over a prompt - entering a feedback loop until two things happen: first, congruence between your intent and the output (both change during iteration! ); second, the output stabilizes with growing prompt length. and so generating the output turns from a slot-machine into something deliberate and personal

(lots of caveats of course but i think it's a worthwhile perspective)

PS -- What I forgot to mention: Its usually a hard fight to get out of the slop zone; The midjourney models have very boring default aesthetics and styles of composition (insultingly boring!)

yeah... AI doesnt seem to make us more creative