~/talk

Bratin Saha, AWS | Supercloud 4

slides:none on file

AWS announces Bedrock GA and adds Cohere models while offering Bedrock private copy for safe fine‑tuning, relaunches CodeWhisperer customization for repo-specific code suggestions, and cites Trainium and Inferentia gains with Trainium and Inferentia performance improving throughput and cost per inference. SageMaker adds private‑beta features that cut training and inference costs by orders of magnitude. HealthScribe appears as a GenAI product. Emphasis is on RAG and vector retrieval, end‑to‑end observability, encryption in transit/at rest, and multi‑model, use‑case‑specific tradeoffs among latency, accuracy, and cost.

AI-written summary · about

  1. 0:00Introduction to Supercloud 4
  2. 0:42AWS AI and ML services update
  3. 3:30Bedrock and SageMaker differences
  4. 5:15Deploying GenAI at enterprise scale
  5. 9:34AI-native vs AI-wrapped apps
  6. 11:22Silicon and throughput for GenAI
  7. 14:30Data modeling and observability
  8. 16:56re:Invent preview
~/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.