I think SwiftUI is just a reflection of the times we live in. If you look around, many things which used to be done at "great" or "amazing" levels, are now just "good enough". Cars, houses, software, service - it all is just a reflection of the attitude, and even I noticed that I follow this in some of my day-to-day decisions.
How much must one tie their self-worth to a chatbot to debase themselves like that? To think that a winner in the arms and intelligence race of animal kingdom, a member of the species that made this chatbot, would put down themselves like that in the defense of the thoughtless silicon is absolutely laughable and depressing at the same time.
LLM proponents always use some language like "these old, stuck up dinosaurs with their manual labor vs us cool smart kids with automated labor", but they forget one thing - with automated labor the performance and cost difference was easily measurable in favor of the automation. With LLMs it's neither measurable nor visible (no better software, no faster delivery overall in the industry), and the costs are pretty bad. Besides personal anecdotes of someone toiling away at yet another AI harness project on GitHub.
It's not just that, but the core is just that, even with reasoning models. Harness can only get you closer to the good result, but can't save you from every pitfall.
As for PM analogy - don't forget that models don't learn and keep doing same stupid stuff they were doing a month ago.
Not only we are looping, we are also adding layers of Idiocracy upon each loop. I kinda envy retired software engineers now, they can just grab the popcorn and watch this dumpster fire without a worry.
For basic primitives with known output it’s verifiable, but as long as you’re dealing with real systems with tons of inputs and side effects this no longer holds true.
> research showing with the right policy,
Rest of the owl.
This article has all the correct conclusions and solutions based on one assumption that doesn’t have any hold in reality - that someone would be insane enough to allow direct DB access to an AI agent.
I think at this point it’s all but confirmed that LLMs sycophantic tendencies coupled with yes-man attitudes produce AI psychosis and AI fanaticism. Especially if you’re already of high opinion of yourself (be it deserved or not).
Yeah, this while video I honestly couldn’t stop chuckling because it’s built on assumption that bicycles somehow either can’t brake at all or will take five business days to brake like a freight train.
Though looking at Berlin cyclists the assumption seems to be true - so many of them insist on just plowing headfirst into an obstacle instead of braking that I start to think that the video was made by one of such cyclists.
It’s so funny reading most comments here, knowing that they’d be celebrating and saying this is good if it was Netanyahu. But when it’s a maniacal islamist declaring his goal to be the destruction of US and Israel, it’s suddenly very nuanced.