Same experience for me. I think people need to start providing context for the type of work they're doing when repeating the local model hype. Maybe they're working with a cookie cutter React app and it does the job fine.
I work on Go and Rust mostly. The experience can be wildly different based on model, quantization, and harness. The fact that it didn't work for you doesn't mean everyone is trying to hype local models, people are getting real work done.
This feels like a symptom of the definition of "real work" changing right in front of us. Some people still use AI like a copilot, cleaning up code here and there, maybe writing functions. And at the right scale, this is genuinely still real work.
Others, especially startups or indie hackers, use AI like it were their end-all be-all assistant. "Hey Jeeves, go add Apple Sign In, Google Sign In to our signup pages. Also, investigate why we're not utilizing cached inputs on our AI APIs correctly. And add Maestro flows for every screen in our app. Btw check out posthog, supabase, and Stripe - is our new agent changing engagement or trial->paid conversion rates?"
And 3 hours later, you have all these done. But only if you use the right multi trillion param models.
In my experience Opus and Claude have declined significantly over the past few weeks. It actually feels like dealing with an employee that has become bored and intentionally cuts corners.
I had to check the date on my phone as I was sure it was an April fools joke. After the absolute onslaught of negative feedback and the new term "Microslop", they put out an article saying you can now adjust the position of the taskbar. Unreal.
No, they put out an article saying that not right now but later this month or maybe next month, if you switch to a beta release, then possibly you'll be able to adjust the position of the taskbar. But at least they have screenshots!
"In researching a hiccup with performance, he stumbled across a file where the OpenClaw agent had downloaded all of his WhatsApp messages and stored them in plain, unencrypted text on his computer. Not just the work-related messages it was given explicit access to, but all of them, his personal messages too."
Now the agent can do the same thing, but it's in a container and it's doing it with a Rust binary, so you know it's safe. /s
reply