Comment by boardwaalk
5 hours ago
I let it go a few hours on a not trivial but well-known problem, and it felt like it was just a little too plodding and just kind of mucked around a little too much and wasn't aggressive enough about getting stuff done. I asked it to wind it down and finish up and it took another hour and 15 to actually stop and commit without really getting much more done. Not very impressed here, if you can't tell. This new version also seems like (maybe this is written somewhere, I don't care to look.) this cycles through compactions every ~250k tokens which, I guess, seems like it might save Anthropic money on KV cache but does net me anything be pretty frequent pauses. (It didn't seem to lose the thread, at least.)
Not gonna say I want 5.0 as an option still... but maybe I do.
The incentives are not aligned. Anthropic makes money when you burn tokens. They also hide the tokens you burn from you, so you can't even validate if you actually burned them, you just have to believe them.
This is not a lasting business model, nor one I'm interested in using.
Commodification of inference cannot come fast enough!
250k tokens is awfully small for a frontier context window, I haven't pushed the frontier models in a long time but i assumed they all had 1M token windows as advertised practically a year ago.
Compaction is a setting that you control in Claude Code.
I experience this with many of the "advanced" models. I find they're actually the most efficient on their low/medium settings, occasionally high. Anything higher than that, and they start inventing more task list items than they check off. They seem to think that every personal project needs extensive adversarial analysis and guardrails and will invent non-issues without being asked.