nethi··on OccupySaaSgoal seems to be to create 1-1 API and feature compatibility, which is very different from various open source IdPs
nethi··on Real-time LLM Inference on Standard GPUs: 3k tokens/s per requestNah. it says it can't even write python code
nethi··on Show HN: A CLI to use any model in your coding agentLooks interesting. How does it work ? And is this all local ?
nethi··on Got fed up with 36 hours of weekly meetings. Built something to fix itIn big companies, sometimes the only way to make this happen is by making the tool mandatory.
nethi··on Understand how transformers work by demystifying the math behind themTrue, but it is the process of climbing trees that gives the insight whether taller trees help or not and if not, what to do next.
nethi··on Ask HN: What is the best Covid-19 dashboard?https://nextstrain.org/ncov tracks genomic epidemiology
nethi··on PipelineDB 1.0 – High-Performance Time-Series Aggregation for PostgreSQLIt seems like if you combine pipelinedb with timescaledb, you get continuous query capability of influx ?