
binfohazard
138 posts



@usr_bin_roygbiv Going somewhere very outside the AI bubble is both comforting and alarming


you ever go outside for like 3 hours and then come back online and remember we are all insane. we've all gone fucking completely insane



@usr_bin_roygbiv wdyt your average number of turns is with a coding agent? Anthropic blog post said average # with Claude code is only 4, which I think is bonkers, but I suppose I do have a decent number of small 1-2 shot tasks throughout the day that bring the avg down

Unpopular opinion: Software engineering is arguably the worst career path today.






Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.


JUST IN: Mark Zuckerberg orders $META to create prediction markets app.



1-bit GLM-5.2 GGUF vs. Claude 4.8 Opus vs. GPT-5.5 We gave 3 models the same prompt and compared one-shot outputs. The 1-bit GLM-5.2 GGUF ran locally on a Mac Studio M3 Ultra with 256GB RAM at ~21.6 tok/s. Which output do you like best? GGUF: huggingface.co/unsloth/GLM-5.…






