A highly beneficial side effect is that it disables the main YouTube shorts stream. You still get some shorts for your subs and such, but the bottomless heroin feed if Shorts is gone, and good riddance.

You can remove shorts under YouTube’s time management settings > daily limits > shorts feed limit, you can set the max allowed time to 0 min and the effect is they all disappear.

Pity this setting is only for the mobile app.

Oh interesting, I just have a userscript that completely excises shorts from youtube, seems like a neat side effect though. Always a jumpscare to use youtube on someone elses computer and see all the shorts, ads, and sponsored segments. We had TiVo like 30 years ago, this is a solved problem.

shorts can be removed using the filters icon at the top right

I came around from fancy everything to just reasonably good beans and an Aeropress. And in the office I'll just saunter to the press-a-button-get-coffee machine, I eventually got tired of the faffing around.

I have the glass and metal Aeropress, so if you fancy the Aeropress but don't fancy boiled plastic, that's an option.

I don't disagree, but I'm not sure I see the point you're trying to make.

Maybe ask your LLM to explain it?

Ah, I see, you weren't making a point, fair enough.

prompt + all other bits of information the context has been seeded with before the output was created (documents, web searches, other sources) in which case it might be more efficient to just consume the final deliverable (yourself or via LLM).

Fair point. We could classify AI generated articles in two categories:

1) articles generated with context data that's trivial to find (or even embedded into the model)

2) articles generated with context data that's hard to find or not publicly available

Ironically a task that an AI agent would have no problem doing.

Yeah, it would have been a great job for an LLM. Although if you find something in the history you then need to make the annoying choice of history rewriting or just leaving it in.

There is also discussion, ping pong with the agent, exploring parallel paths, quickly experimenting, analyzing code, researching things. A code agent can do more than "write me as much code as possible, go!".

That's how I use agents, but I see less experienced engineers brag about how much code they pump out and it makes me cringe

Alphabet makes $30 billion profit per quarter.

> Alphabet makes $30 billion profit per quarter

Sure. Neither OpenAI or Anthropic do. Amazon and Google have followed institutional investors bidding up Anthropic over OpenAI in private markets, all of which—I suspect—followed user-pattern shifts following the fiasco. (Well, fiascos. Altman is a host unto himself.)

Which means they can allow themselves to blast money left and right? Its still a big investment.

they can't allow themselves NOT to blast money left and right

Yes

No, they have a fiduciary duty to shareholders to not make obviously bad investments.

At least oats don't have to be perpetually kept pregnant while taking their offspring away from their mothers. See, snide comments cut both ways.

Indeed. I’m only making the suggestion that the metric might not be good as a proxy.

It’s a brutal business.

I see someone has no idea how farming actually works.

Why don't you enlighten us?

So, how does aj engineer new to a code base add new features? They read the code base, understand the architecture and structure and make changes. An agent can do the same.