“I found ways to bring joy, slowness and thoughtfulness to myself — because cancer or not, we need those things to survive.” 💖
— Entrepreneur, activist and cancer survivor @kavitarai_
Did you know thta the real world still works on days
people dont answer phones and emails after 5pm
people take days to reply
people take days to look over documents
people take days to read replies and reply.
its slowness is insane.
web3 has spoiled / ruined me.
i cant even:
go for a walk without reading a book
watch a movie without my phone
goto sleep without an audiobook
tell myself i will do it tomorrow...exepct when i have no alternative
Yesterday, I met with a group of young men and women from the Western Mountains to discuss the outcomes of the Structured Dialogue, the agreement of the Smaller Convening and the importance of advancing the political process to achieve unified institutions and national elections. We also discussed the different ways youth can engage in the political process. They requested increased youth representation and highlighted the important role youth can play in national reconciliation and finding a way out of the political deadlock. They also expressed their frustrations at the impact of the political deadlock and slowness at finding a solution, the rising prices impacting families, the challenges with healthcare and education, and stressed how much they want a Libya which supports everyone to have a prosperous future.
UNSMIL is continuing to engage youth from across the country to ensure their voices and concerns are heard in relation to the political process and meeting the needs of the youth.
If your terminal ever gets into a 'bad state', like garbled outputs, you run 𝚛𝚎𝚜𝚎𝚝. I noticed it was… oddly slow.
Turns out in 1979 3BSD's 𝚝𝚜𝚎𝚝 had a 𝚜𝚕𝚎𝚎𝚙(𝟷) to let mechanical printer-and-ink terminals 'settle down' 😂
I asked 𝚏𝚡 to write me a faster alternative in Zig. It takes 1ms instead of 1s. It was really cool to dive deeper into 𝚗𝚌𝚞𝚛𝚜𝚎𝚜, 𝚝𝚜𝚎𝚝, 𝚝𝚎𝚛𝚖𝚒𝚗𝚏𝚘, and the myriad ways in which your terminal can get… cursed.
It's legit fascinating how far back our technology stack goes, and how enduring good system design is, even with the occasional 'spider webs' you can find.
Check out for a fun explainer (and some alternative solutions.)
ps: once you start using 𝚏𝚡, you'll notice slowness like this everywhere :D
"It feels slow" is the worst ticket a self-hosted LLM generates.
vLLM starts, serves, and reports success whether it's configured brilliantly or wastefully. Nothing tells you which.
But the answer is already sitting on /metrics: latency split by phase, cache hit rates, batch occupancy, completion outcomes. Almost nobody scrapes it.
On a single A10G, 6 metric checks turned "it feels slow" into a verdict:
TTFT: 51 ms against a 300 ms p95 target
Queue time: 0.01 ms
Decode: 97% of total latency
Prefix cache: 32% of prefill work skipped entirely
The server was over-provisioned, not under. The slowness lived somewhere in front of it: the app, the gateway, or the prompt.
Tuning an LLM server is reading telemetry and reasoning about saturation. SREs have been doing that for 20 years.
Full walkthrough with the ES|QL queries, the DCGM setup, and all 6 metric checks on an A10G: