“You may need a bit of fine-tuning of your probes so that they work on each person's particular fine-tuned model”
EB
Eric Bigelow
"The Cognitive Revolution" ·
“We asked inkling to fine tune itself using tinker. The model wrote its own fine tuning job, ran it and evaluated the result.”
Everyday AI Podcast - An AI and ChatGPT Podcast · Ep 876: The Most Important AI Model You’ll Probably Never Use That Just Dropped (Replay)
Play from 7:35
7:35
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
built an Inkling playground in Tinker where the model fine-tuned itself by writing its own fine-tuning job, running it, and evaluating the result
Said nearby on the same subject
“Can't you just run an automated agent now that does that daily to where you don't even have to fine tune it?”
♫
Said on Dropping Bombs
“The trick is just externalize to a file system… force everything to run through code, you know, trust the model that can write code and it's going to write its own harnesses itself”
♫
Said on Latent Space: The AI Engineer Podcast
“We trained for 90 steps, with three seeds for each fine-tuned character model, nine runs in total… using Impossible Bench… broken tests… model could only get the reward if it tampered with the tests.”
♫
Said on LessWrong (Curated & Popular)
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.