danielbln

This made me chuckle because it's so true. So much detailed steering and finagling in the past, now I point the agent to a bunch of information sources, skills, similar repositories that might hold useful input and tell it very roughly what I need and off it goes, I'll grab coffee.

AI of being forced within the limits of their training

AI doesn't exist in a vacuum, it's the sum of training, inputs and outputs. If I give it novel inputs, the outputs won't be solely within the limits of their training. If I use it as part of a pipeline, the end result of the pipeline too won't be forced within the limits of AI training.

Yeah I hear that all the time "someone needs to clean up the slop tech debt" yet in the before times there was plenty of tech debt no one ever cleaned up, why would that be different now.

And that sort of yak shaving is something LLMs are great at.

I don't see why a strong model wouldn't significantly outperform any human in this sort of low level optimization work. We don't hand optimize assembly either.

The competitive edge lies with the higher attraction layer, not the nitty gritty implementation detail (any more). Is that still software programming? The human work lies in the what and why and in broad strokes how

No one is stopping you. It's only if you want someone to pay you for hand writing code that you might feel a certain competitive pressure that makes it economically difficult, let's say.

Seeing how Anthropomorphic just reset usage quotas back to 0 and the other day extended Fable sub inclusion by a few days, I have a feeling they might not drop Fable out of sub after all, because like you I would most definitely take a long good look at codex at that point.

Im here for it, good on Anthropomorphic to feel some heat again after all that drug dealer Fable business.

Agreed, you can feel this change strongly with Opus vs Fable. Fable doesn't feel like a junior developer anymore. And it requires a lot less ceremony to boot.

I hate hate hate level scaling. I believe they also introduced it to WoW, which ruins the power fantasy of going back to a lower level area and kicking butt, or the fear of venturing in a higher level area and hauling ass out of there. I agree, lazy game design.

And now you've added to the pile, congratulations.

They add nothing, meaningless anecdotes. I was kind of riffing on that.

And I've been quite impressed. Opus talks the talk, Fable walks the walk.

You didn't add "make no mistakes" so that first test burn will probably blow up the pad, but now you know.

Have you asked an actual cashier what they think? They handle hundreds of people every day, do you really think they consider it rude if people don't chat them up? You can smile and say hello and thank you with or without headphones. This once again seems like a cultural divide, as a German I'm happy if noone talks to me outside of smiles and hello/goodbye, this might be different in the anglosphere.

Ah, you must be one of those enlightened centrists that doesn't recognize a shifting overton window even if it grabs you by the....

Not everyone who likes something that you don't like is an X-bro, so maybe that clears things up.

I think there are some gems in the media space, the Lord Of The Rings Disco song is a certified banger, AI or not.

But yes, there is so so much slop as well

Yeah 60k is ludicrous, I've barely seeded the context at that point and I don't see context related degradation until well into the 600-700k.

There were no outages before AI, also no bad code and every PR was a work of art.

This is me. I found AI to be an incredible provider of structure, focus and productivity, its an externalized executive function provider. No longer do I forget what last week's meetings were about, no longer am I paralyzed by seemingly I surmountable tasks it all just flows, and I get to rubber duck against an endlessly patient system. I love it, and I'm somewhat bewildered by some of the takes in this thread. Different strokes for different folks, I suppose.

Berlin "boutique" tech consultancy, we are seeing a noticable increase in Israeli and US engineers into our hiring pipeline. The braindrain from the autocratic countries is real.

Please no, I need my vacuum to work reliably in every room.

I can (and do!) pay the power company a pittance to run a surprisingly strong local model on a little box next to my keyboard, that does a fine job. Maybe not as fine as the billionaires thinking machine, but good enough and often better. Given that fact, I consider reliance on LLMs as much of an "issue" as reliance on a computer.

I would have killed for access to an LLM during school. Not to do my homework (though that too, homework is an antipattern imo) but to fill my gaps at my own pace and level of patience. Just endlessly pestering the AI "ok, but why?" until I grokked it.

You handle large code base by enforcing best practices that should have always been enforced. Proper up to date documentation, strict adherence to conventions and coding guidelines, cross review of deliverables, TDD, and so on. Just whispering "make me a dashboard" into the machine's ear is not how you drive agents to create maintainable and understandable code.

Fair enough, so it's a misnomer. Let's call it task switching then, since we don't actually do tasks at the same time, but switch from one to the other. A Claude Code session helpfully prints a small tldr summary of the ongoing session, so that one can quickly onboard again to the task at hand. I do not find that draining, personally.

Don't be so dismissive. Every person is different, and you struggling with multitasking doesn't mean everyone is.

Ok, I guess this is outdated then because I did what I said I did.