~/talk

Inspect the House, Not the Neighborhood: What Actually Makes an AI Model Risky

slides:none on file

A fake Hugging Face model hits 244,000 downloads by faking an OpenAI repo and ships malware in a setup script; JFrog finds ~100 models with malicious payloads hidden in pickles and research shows ~250 poison documents can implant backdoors. Practical controls include three habits—safe tensors, pin to a commit, and disable remote code—and routing every agent through one gateway and per-workspace configs so a model can be shut off or swapped. Cost examples include a $300/year customer agent and mixed self‑hosted economics.

AI-written summary · about

  1. 0:00Introduction by Gene Kim
  2. 1:43The fake model on Hugging Face
  3. 3:10Are we using Chinese AI?
  4. 8:08Inspect the house, not neighborhood
  5. 12:02Malicious files, not model weights
  6. 13:52Doors: data and agent access
  7. 18:13Treat the model as replaceable
  8. 21:01Checklist and homework
~/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.