~/talk

Mark Heaps, Groq | theCUBE + NYSE Wired Media Week - Cyber & AI Innovators Summit

links:none on file
slides:none on file

Update on Groq’s inference platform: the company claims jump from 60 to 650,000 developers on its cloud API, pushes ultra‑low latency inference with the language processing unit LPU optimized for tokens per second and first‑token time, ships full racks for large deployments including racks shipped to Saudi Arabia, and recommends cloud API first then scale to on‑prem for tens of millions of users. Demonstrated real‑time apps—transcription, voice conversational agents, recommendation/dating prototype—and emphasizes cost and efficiency at scale.

AI-written summary · about

  1. 0:00Intro
  2. 0:45Groq
  3. 2:53OnPrem
  4. 6:12Scale
  5. 8:03Deployment
  6. 10:04Developer Appetite
  7. 14:02Human in the Loop
~/search
type to search 6,518 conferences, 143,918 speakers and 192,133 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
← →
on a talk: 5 seconds back / forward
0–9
on a talk: jump to 0%–90% of the recording
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.