Remix.run Logo
Remix clone Hacker News
new | show | ask | jobsGithub
▲ benswerd 2 hours ago

I predict LLMs will reach superhuman level and beat even that model in the next 12 months

▲orbital-decay 2 hours ago | parent [-]

Starcraft is APM-dependent. Unless the latency will improve greatly in frontier reasoning LLMs (which is unlikely), it will remain a bit like knitting with an excavator.

▲benswerd 2 hours ago | parent | next [-]

I predict latency will improve greatly in the next 12 months to more than 4x speed on current frontier tasks

▲loeg 2 hours ago | parent [-]

Yeah but Starcraft needs, like, 10-20x the APM these agents are doing.

▲benswerd 2 hours ago | parent [-]

I’m not convinced a lot of it can’t be solved with code mode.

Marine staggering for example seems like an ideal code mode task.

▲loeg an hour ago | parent [-]

Yeah. Some of it may just be "thinking" less rather than faster token generation.

▲jamiequint an hour ago | parent | prev [-]

Should be possible to play this with Jev.