Every other week it's a new "X didn't matter, until Y date" without any hard quantitative claims.

It's crazy how over the past years a field originating from math ends up succumbing to subjective feels.

It's a forum, not an engineering conference, but here is a demonstrated 10 point difference between two top harnesses anyways: https://artificialanalysis.ai/agents/coding-agents#harness-c...

Because they want to play teams and act like there's "good" companies,

all the while they throw their bank account and whatever they want at GPT or Claude models.

As long as people keep gaslighting by sayting those events are just "skill issues," I doubt there will sadly be a catalyst.

Yeah, this will never happen until governments step in and cause these companies real pain. I mean just look at Crowdstrike. They caused billions and billions in economic damage due to their incompetence, and nothing happened. In fact, their stock is close to an all time high.

It's less "can't be bothered to read through it because we know where it came from" and more "can't be bothered to read through it because of how word-salad it is"

Unless heavily prompted the written output is always so dense that you can barely understand it.

Everything is "rectifiable with the right prompts" if you handwave the hallucinations it makes (which yes, even frontier models do. Or I guess all companies that had major outages within the past months were using fossil models).

And it's funny this same argument can be said since Sonnet 3.7. But the issues still pop up.

we've advanced significantly since 3.7

It's just the new thing.

People were hyping up Oh My Opencode. When they realized it didn't lead to any significant gains in performance they hopped on the next thing.

And when the same thing happens to Superpowers it'll be something else they cling on because "this time it's different"