~/talk

Questions for Theory in the New Age of Machine Learning

links:none on file
slides:none on file

Argues that LLMs become the learning substrate: using GPT-4 to generate justifications from 125 examples of CK-12 hints, distilling them into seven principles rubric that boosts classification without numeric parameter tuning; builds a running agent called Predict Anything that searches web sources (FRED, Google Trends), writes Python data-fetching code, logs per-function traces for Claude to self-reflect, and iteratively improves tasks; reports an unemployment prediction moving 4.30% → 4.23% and finds school-calendar signals improve flu forecasts.

AI-written summary · about

  1. 0:00Workshop introduction
  2. 3:56Conventional ML wisdom
  3. 7:12Challenging ML assumptions
  4. 10:32LLM justifications for classifiers
  5. 18:11Predicting without features
  6. 24:14Agents writing their own code
  7. 31:48Theory opportunities in ML
  8. 33:36Audience discussion and reflections
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 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
?
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.