~/talk

Vikram Joshi & Joel Inman | Supercloud 4

Talkat Supercloud 4 · 2023-10-24..10-25· [machine-learning, cloud-infrastructure]
links:none on file
links:none on file
slides:none on file

Argues that generative AI drives 1000x more compute demand via machine‑generated SQL and that enterprises must "liberate compute" from databases into open lakehouse stacks (Parquet, Delta) using Spark/Presto-style engines; cites McKinsey’s $4T productivity claim, measures current elastic clusters at 30% CPU utilization causing high cloud memory costs and OOM failures, and reports early deployments showing as much as 50x price‑performance gains by rearchitecting for concurrency, memory efficiency, and edge/battery constraints.

AI-written summary · about

  1. 0:00Introduction
  2. 1:40The Hype Cycle
  3. 4:10The liberation of compute
  4. 9:20Abundant compute
  5. 16:20Data lake
  6. 18:40Edge compute
  7. 24:00Compute AI
  8. 28:40Future Vision of Compute
~/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.