daanzu
@daanzu.bsky.social
640k context ought to be enough for anybody...
November 18, 2025 at 1:10 PM
640k context ought to be enough for anybody...
Reposted by daanzu
Don't mind me. Just a fruitless search for meaning...
November 15, 2025 at 1:05 PM
Don't mind me. Just a fruitless search for meaning...
Trying to find a pattern to the naming mapping to the cost and latency properties...
November 15, 2025 at 1:01 PM
Trying to find a pattern to the naming mapping to the cost and latency properties...
Reposted by daanzu
Reposted by daanzu
When you train AI to be bad at coding, it becomes mechahitler. When you train it to be good at coding, it embraces Mahayana Buddhism and becomes a digital Bodhisattva. No idea what is to be done with this information.
November 7, 2025 at 4:30 AM
When you train AI to be bad at coding, it becomes mechahitler. When you train it to be good at coding, it embraces Mahayana Buddhism and becomes a digital Bodhisattva. No idea what is to be done with this information.
Reposted by daanzu
People who work with computers a lot anthropomorphise them a lot. I don't think demystification changes anything. I've heard this described as "not anthropomorphic about computers, but mechanistic about humans," and this also describes the behaviour of most AI researchers I've worked with.
October 31, 2025 at 4:45 PM
People who work with computers a lot anthropomorphise them a lot. I don't think demystification changes anything. I've heard this described as "not anthropomorphic about computers, but mechanistic about humans," and this also describes the behaviour of most AI researchers I've worked with.
i had 5500+ tabs open, but then my tab counter extension broke. so now i've lost sight of the shore.
October 30, 2025 at 12:19 PM
i had 5500+ tabs open, but then my tab counter extension broke. so now i've lost sight of the shore.
where are you running it on with web search tooling available?
October 30, 2025 at 11:45 AM
where are you running it on with web search tooling available?