HackerTrans
TopNewTrendsCommentsPastAskShowJobs

dotnot

no profile record

Submissions

Why LLMs will be always Terrible at Software Architecture

devforth.io
3 points·by dotnot·قبل شهرين·0 comments

LLM Terminology explained simply: Weights, Inference, Effective sequence length

devforth.io
5 points·by dotnot·قبل 4 أشهر·1 comments

[untitled]

1 points·by dotnot·قبل 4 أشهر·0 comments

Real-world GPT-OSS-20B benchmark on L4, L40S and H100 (latency, tokens/SEC)

devforth.io
1 points·by dotnot·قبل 5 أشهر·0 comments

comments

dotnot
·قبل 4 أشهر·discuss
Nice readme example, I would also like to see time of execution for these tasks, I mean how much time for handling filters adds comparing to non using it