I am not sure how trillions of computations will occur, simply attempting 0-255 would have found ... all? ... of the eMudhra fuckups. Maybe a few million instructions burnt on a CPU.
Yes I have similar anecdotal experiences - it gets dumb before a new model. What I imagine in my head is Anthropic using all their GPUs to polish off the next model and they need to borrow GPU cycles so they cut down the thinking.
Is this the thing that started prompting me to approve curls against JIRA because the Authorization header is `my_email@domain:$API_KEY_ENV_VAR`? Why does it not respect --dangerously-skip-permissions?
Hi, thanks for Claude Code. I use it, and it works well. Have you considered changing it so the text comes down from the top of the screen, in green, like The Matrix?
+1 for Kagi, even if Maps and Shopping and Images aren’t as good as Google (tbh their Images search is good enough 8/10 times) they’ve got the actual web search stuff working quite well.