Distillation, or, How to Steal a Model

Distillation, or, How to Steal a Model

This week we’re covering model distillation: the technique of using a large "teacher" model's outputs to train a smaller, cheaper "student" model that mimics it. They cover the two big reasons labs do this — making lighter, faster, more focused models for specific tasks, and the more contentious use case of effectively copying a rival's flagship model by hammering its API with questions (with a callback to the old Bing/Google search controversy). They also get into why it's so hard to prove distillation happened, why some models occasionally introduce themselves as "Claude," and a surprisingly old idea: a 2015 paper by Geoffrey Hinton, Jeff Dean, and Oriol Vinyals on distilling knowledge using the full probability distribution over a model's outputs — not just its single most likely answer — and what that "soft label" approach captures about how a model relates concepts to each other.

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(317)

Invisible LLM Failures and AI Fluency with Chris Potts (Stanford)

Invisible LLM Failures and AI Fluency with Chris Potts (Stanford)

What happens when a Stanford linguistics professor turns his attention to AI chatbots — and the surprisingly invisible ways humans misunderstand them? Chris Potts joins the show to unpack the hidden f...

20 Juli 41min

Still summer break: back next week

Still summer break: back next week

Still summer break: back next week by Katie Malone

13 Juli 25s

Summer break: back soon

Summer break: back soon

Summer break: back soon by Katie Malone

6 Juli 36s

Interviewing the Linear Digressions Agents (The Agents Season, Episode 11)

Interviewing the Linear Digressions Agents (The Agents Season, Episode 11)

After a five-year hiatus, the podcast that burned out partly over the tedium of writing episode descriptions is back — and using AI agents to handle exactly that task. The season-11 finale turns the l...

28 Juni 37min

Agent Economics (The Agents Season, Episode 10)

Agent Economics (The Agents Season, Episode 10)

What if building more highways made your commute *slower*? That's the paradox at the heart of AI agent economics: even as per-token inference costs have plummeted dramatically over the past two years,...

22 Juni 24min

Agent Trust, Oversight and Control (The Agents Season, Episode 9)

Agent Trust, Oversight and Control (The Agents Season, Episode 9)

Capabilities get all the attention when it comes to AI agents — but what happens when a highly capable agent makes a bad decision in the real world? Trust, oversight, and control are the unglamorous b...

15 Juni 25min

Many Agents, Many Problems (The Agents Season, Episode 8)

Many Agents, Many Problems (The Agents Season, Episode 8)

Whether you work best solo or thrive in a team, you know collaboration is complicated — and it turns out AI agents face the same tensions. This episode dives into multi-agent systems, exploring how ne...

8 Juni 28min

Populärt inom Teknik

uppgang-och-fall
elbilsveckan
market-makers
natets-morka-sida
skogsforum-podcast
rss-technokratin
rss-elektrikerpodden
developers-mer-an-bara-kod
rss-uppgang-och-fall
allt-du-behover-veta-om-ny-teknik
bilar-med-sladd
rss-sakerhetspodcasten
rss-fabriken-2
rss-veckans-ai
trevligt-snack
solcellskollens-podcast
bli-saker-podden
rss-heja-framtiden
vi-bilagares-podcast
rss-digitala-influencer-podden