toastmaster11

All that stuff you mentioned is derived from a core set of principles established by decades of software best practices applied to a new means of generating code. Like quite literally those instruction files/skills essentially just reiterate the practices themselves.

To your last paragraph, I never say that nor do I imply it. I find that as a pretty disingenuous interpretation of what I said actually. The practices I mentioned were derived from hard learned lessons and designed as a means of mitigating the human tendency to write bad code.

If the vibe coders are right I would give at least 90% of the credit to all the well made libraries, rules, and best practices that developers have built up over the decades. That’s what is embedded into LLMs and what might be the saving grace of slop code bases in the future.

I am GP, reading comprehension and such.

Concurred

How much pontificating needs to be done before people acknowledge nobody has any idea what to do with AI on an individual level?

First being good developer and learning how to use AI was sufficient, next it was being able to design architecture, then it was “taste” that made all the difference and now being an expert in the domain is the only thing that matters really.

Until AI is basically in a stable, predictable, state of improvement or stagnation, these takes will continue to be pointless and most likely completely wrong.

Profound political commentary?

I find the most miraculous thing about 4.7 to be that the pelican is facing left, wonder why the right facing everything is so ubiquitous in these images.

What happened that placed Opus 4.6 on max reasoning below Sonnet 4.6 on a lowered reasoning level?

What exactly is the hard part they’re describing? Taste? Picking a stack? Noticing drift?

Seems like the “harder and vaguer thing” would be explaining to someone why that’s even necessary, or why your particular taste or stack of choice are any better than what the AI would choose itself.

Kinda silly when the whole point of the piece is “don’t invent fake things to justify your work”.

I’m asking, why is it 4.5-turbo when 4.5 isn’t released yet?

But why would it be gpt-4.5-turbo, as opposed to just gpt-4.5? Are they just going to abandon past naming conventions?

If they already had 4.5 and then did something else to make it “turbo” why not release 4.5 on the coattails of Gemini?

Another perspective, wouldn’t it be reasonable to believe that the faster a technology is developed, the faster it will reach its theoretical upper limit of improvement (assuming there is one)?

To use your comparison as an example, mainframes took 40ish years to be replaced by personal computing and distributed systems. Whereas smartphones reached modern parity in 8-10 years since the original iPhone and have made more or less incremental changes since.

Granted those are hardware changes and this is software but I believe the point still stands.

Sumplete is not an original game. Though points for an original name however.

https://gizmodo.com/chatgpt-copy-sumplete-puzzle-game-summer...

Artificial intelligence creates a more compelling narrative. It’s the “us .vs. them” dynamic that humans are so fond of. Even when it isn’t an explicitly antagonistic relationship; an AI is still shown as an “other”.

Really when you think about it, in a good amount of stories humans might as well be augmented intelligences. We just aren’t making a point of them being different, or at odds with the general human population.

I think the human need to feel useful, or to produce something is more sociological than a base human need.

When/if that becomes an issue, if social rejection was not a consequence of not being productive more people would be okay with simply participating in things for their own sake.

For example, I don’t play Stardew Valley because I want to be the most elite virtual farmer.

I agree that is the ideal scenario, but what are the actual incentives for implementing A system like that?