I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
Works now, I had a wrong miniaudio config! Roundtrip is now 29.5 ms. Turns out we should not ask WASAPI for a samplerate at all, and not for a specific buffer size, it wants to default to 480 frames then. Even if we ask *the same* samplerate. Good to know.
@anthropic Sonnet vs @X Grok Build.. Never thought this would happen, but Grok Build fixed the entire problem first try, while Sonnet 5 failed miserably three reverted sessions in a row. That is strikingly odd.
Anthropic, did you nerf Sonnet 5?
I quit using your service, but I have no alternative, so reluctantly I restarted my subscription. But now it feels like the Sonnet 5 model has been thrown back a year.
Mistake after mistake after assumption after assumption.
What is going on?
Anthropic Sonnet 5 seems to have regressed into ADHD, it was pretty good before. Now it does not read, it makes a LOT of assumptions, ignores all of its own memories, and wants to be done quicker, with all kinds of bad side effects.
Claude Sonnet 5 C++ comment removal campaing, 8k lines of comments (>2 lines) in my 200k code line code base, oh boy.
What do they feed these models?
Sonnet 5 sure loves code comments. I now need to have sessions to remove comment diaries and code explaining comments, because it is filling the code base with useless comments. Comment rules are: 2 lines max, never explain code -> code smell, never comment on removed code. Sigh.
Ah, AstroBasic FlightSim is up an running again, neglected it too much while the compiler evolved.
It comes as a demo for for the compiled language, for users to tinker with, do you like it?