let_tim_cook_
Re:Cosmologically Unique IDs
on Thursday February 19, 2026 @06:11AM (#47072573)
"372 bits for 1-gram nanobots"... smh, this is why people call us nerds
Re:LoRA Without Regret
on Saturday October 04, 2025 @12:14PM (#45474391)
I'm not sure why progressive LoRa merging needs to be addressed here. They show there is a regime of problem where LoRa performs equivalently to FFT.
Progressive merging of LoRa is somewhere inbetween and categorically more complex than just LoRa so would be dominated by standard LoRa in that case.
While progressive merging could train faster as fewer params are trainable at any given time, it results in very larger adapter diffs OTO the size of the original model and doesn't retain the benefits of being able to deploy multiple adapters over the same base model idt.
Re:OpenTSLM: Language models that understand time series
on Wednesday October 01, 2025 @02:11PM (#45441078)
"Stanford Repo Released Sep 31, 2025" Seems like something sampled from a distribution with non-zero probability that the day after Sep 30, 2025 would is the 31st....
Re:Clankers Die on Christmas
on Monday September 08, 2025 @12:53PM (#45170641)
Sounds like something a clanker would write....
Re:AI Agent Benchmarks Are Broken
on Friday July 11, 2025 @10:37AM (#44532633)
Are any authors here? Have you looked at AppWorld? https://appworld.dev