~/talk

Detecting 70 Kinds of Bias with a Model You Own: Replacing LLMs

links:none on file
slides:none on file

Collects news from X and Google News, deduplicates and threads stories, then queries OpenAI, Anthropic, Quen, Croak and Deep Seek with an expert-written five-LLM wrapper; PhD linguists build a taxonomy and resolve disagreements; specialist small models double-check labels; team trains a single model trained on ~500,000 balanced stories that flags 70 bias labels at the sentence level, highlights spans, and suggests edits. The result runs in one pass, costs a fraction of five APIs, is more consistent, and uses a monthly retraining loop.

AI-written summary · about

  1. 0:00Intro
  2. 0:53Why Linguistic Bias Matters
  3. 4:04Collecting News from X and Google News
  4. 5:17Deduplicating Stories
  5. 6:59Five-LLM Wrapper and Disagreements
  6. 10:04Human Experts in the Loop
  7. 15:11Training Our Own Bias Model
  8. 18:29Benchmark: Consistency, Speed, Cost
  9. 20:15Monthly Retraining Loop
  10. 21:34Four Lessons and Recap
~/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.