Oh good call
Weird, yeah it works for me
Claude Code hasn't updated yet it seems, but I was able to test it using `claude --model claude-opus-4-7` Or `/model claude-opus-4-7` from an existing session edit: `/model claude-opus-4-7[1m]` to select the 1m context…
Claude Code doesn't seem to have updated yet, but I was able to try it out by running `claude --model claude-opus-4-7`
I was a kid who started shaping surfboards as a hobby shortly before this happened. The hectic-ness was real — it was almost impossible to find a foam blank afterwards, they were more expensive, and they felt noticeably…
Note that I get a similar speedup with 6 and 8 threads on my Mac (which has 8 logical CPUs)
This experiment is a bit weird. If you look at https://github.com/matklad/lock-bench, this was run on a machine with 8 logical CPUs, but the test is using 32 threads. It's not that surprising that running 4x as many…
Oh good call
Weird, yeah it works for me
Claude Code hasn't updated yet it seems, but I was able to test it using `claude --model claude-opus-4-7` Or `/model claude-opus-4-7` from an existing session edit: `/model claude-opus-4-7[1m]` to select the 1m context…
Claude Code doesn't seem to have updated yet, but I was able to try it out by running `claude --model claude-opus-4-7`
I was a kid who started shaping surfboards as a hobby shortly before this happened. The hectic-ness was real — it was almost impossible to find a foam blank afterwards, they were more expensive, and they felt noticeably…
Note that I get a similar speedup with 6 and 8 threads on my Mac (which has 8 logical CPUs)
This experiment is a bit weird. If you look at https://github.com/matklad/lock-bench, this was run on a machine with 8 logical CPUs, but the test is using 32 threads. It's not that surprising that running 4x as many…