How do thinking and reasoning models work?
25 012
9.3
Next
40 days – 3121:01Popular
33 days – 44 2886:32
39 days – 27310:00Published on 3 Dec 2025, 17:59
LLMs that can "think" and "reason" have become increasingly popular. But what is a model actually doing when it's "thinking" and how can we train LLMs to be better at reasoning? This explainer video covers the fundamentals of how thinking models work, including concepts like scaling laws, test-time compute, and reinforcement learning from verifiable rewards.
Resources:
Gemini thinking → goo.gle/3KaUL0J
Subscribe to Google for Developers → goo.gle/developers
Speaker: Nikita Namjoshi
Products Mentioned: Google AI
Resources:
Gemini thinking → goo.gle/3KaUL0J
Subscribe to Google for Developers → goo.gle/developers
Speaker: Nikita Namjoshi
Products Mentioned: Google AI
Fresh videos
5 days – 41 2691:27
6 days – 24 8522:55
12 days – 3896:44
13 days – 1633:15
21 day – 79 79115:20Random videos
206 days – 8 7470:22
215 days – 1462:40
250 days – 225 7840:49
15.07.24 – 3342:36
23.01.24 – 84 2950:34
02.06.21 – 20 71944:50
4 hours – 1 2840:31
3 days – 4 5661:32
5 days – 4947:18
12 days – 111 1331:06
13 days – 2353:32
13 days – 6 6430:31
13 days – 892:42
3 days – 1 1500:53