Kanjun Qiu: AI emergent capabilities are artifacts of evaluation metric design
Kanjun Qiu · Building Human-Level AI Agents: Imbue CEO Kanjun Qiu on the Road to General Intelligence · Oct 4, 2023 · at 21:11
Kanjun Qiu, CEO of AI startup Imbue, explains how evaluation metrics impact whether AI capabilities appear to emerge suddenly or improve continuously.
0:00 / 0:12exact quote · 12.8s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“If your metric is smooth you actually see slow performance improvement over time, and if your metric is relatively discrete or not smooth, that's where you see the emergence, and it's actually more about the evaluation metric Than about the emergence of the capabilities.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Kanjun Qiu
Qiu: AI is currently in an un-reliable analog computer phase
“I think today, you know, we're kind of in the analog computer phase of AI, where You know, ah, these systems, they output things. Errors compound. They're not very reliable.”
Kanjun Qiu: Language models trained without code perform poorly at reasoning
“Some companies have tried training language models with no code because they're like, oh, the product we're building, we don't need code. You know, it's a therapist or it's a question answering thing and we don't need code. So we should take code out of our tr…”
Qiu: Psychological trauma can be conceptualized as computational overfitting
“Trauma is overfitting and actually a good way to overcome trauma. If we look at a lot of therapy It's like by giving more data to me and helping me access the overfit parts and then give them more data.”
Kanjun Qiu: Self-supervised learning mirrors how humans naturally learn
“Self-supervised learning is interesting because it's how humans learn, you know, most of the time we go around We like Google stuff. We learn on our own. We're not giving supervised labels all the time.”