Artwork

Kandungan disediakan oleh BlueDot Impact. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh BlueDot Impact atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.
Player FM - Aplikasi Podcast
Pergi ke luar talian dengan aplikasi Player FM !

Illustrating Reinforcement Learning from Human Feedback (RLHF)

22:32
 
Kongsi
 

Manage episode 429711881 series 3498845
Kandungan disediakan oleh BlueDot Impact. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh BlueDot Impact atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.

This more technical article explains the motivations for a system like RLHF, and adds additional concrete details as to how the RLHF approach is applied to neural networks.

While reading, consider which parts of the technical implementation correspond to the 'values coach' and 'coherence coach' from the previous video.

A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.

  continue reading

Bab

1. Illustrating Reinforcement Learning from Human Feedback (RLHF) (00:00:00)

2. RLHF: Let’s take it step by step (00:03:16)

3. Pretraining language models (00:03:51)

4. Reward model training (00:05:46)

5. Fine-tuning with RL (00:09:26)

6. Open-source tools for RLHF (00:16:10)

7. What’s next for RLHF? (00:18:20)

8. Further reading (00:21:17)

83 episod

Artwork
iconKongsi
 
Manage episode 429711881 series 3498845
Kandungan disediakan oleh BlueDot Impact. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh BlueDot Impact atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.

This more technical article explains the motivations for a system like RLHF, and adds additional concrete details as to how the RLHF approach is applied to neural networks.

While reading, consider which parts of the technical implementation correspond to the 'values coach' and 'coherence coach' from the previous video.

A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.

  continue reading

Bab

1. Illustrating Reinforcement Learning from Human Feedback (RLHF) (00:00:00)

2. RLHF: Let’s take it step by step (00:03:16)

3. Pretraining language models (00:03:51)

4. Reward model training (00:05:46)

5. Fine-tuning with RL (00:09:26)

6. Open-source tools for RLHF (00:16:10)

7. What’s next for RLHF? (00:18:20)

8. Further reading (00:21:17)

83 episod

ทุกตอน

×
 
Loading …

Selamat datang ke Player FM

Player FM mengimbas laman-laman web bagi podcast berkualiti tinggi untuk anda nikmati sekarang. Ia merupakan aplikasi podcast terbaik dan berfungsi untuk Android, iPhone, dan web. Daftar untuk melaraskan langganan merentasi peranti.

 

Panduan Rujukan Pantas

Podcast Teratas