~/talk

GenAI Adoption, Challenges & Anti-Patterns

name:Topo Pal
links:none on file
slides:none on file

GenAI speeds tasks from months to hours yet breaks assumptions: a software bill of materials dashboard that took five days plus three weeks to production a year ago now lands in one day, and 5% of users consume 75% of tokens. Models used include GPT‑4.1 and Sonnet 4.5; token‑saving preprocessors often reduce correctness; 100x throughput overwhelms a 1x SDLC; premature standardization of prompts/skills fails; experienced engineers focus on assumptions, preserved behavior, risks and operational controls.

AI-written summary · about

  1. 0:00Introduction by Gene Kim
  2. 7:00GenAI for general productivity
  3. 8:21GenAI in engineering teams
  4. 13:44Rethinking the SDLC
  5. 17:13Token spend and ROI
  6. 18:55Benchmarking coding agents
  7. 21:08Premature standardization anti-pattern
  8. 23:59Final thoughts for engineers
~/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.