Difference between revisions of "Constitutional AI"
m |
m |
||
| Line 16: | Line 16: | ||
* [[Reinforcement Learning (RL) from Human Feedback (RLHF)]] | * [[Reinforcement Learning (RL) from Human Feedback (RLHF)]] | ||
* [https://medium.com/mlearning-ai/paper-review-constituional-ai-training-llms-using-principles-16c68cfffaef Paper Review: Constitutional AI, Training LLMs using Principles] | * [https://medium.com/mlearning-ai/paper-review-constituional-ai-training-llms-using-principles-16c68cfffaef Paper Review: Constitutional AI, Training LLMs using Principles] | ||
| − | + | ||
| − | |||
| − | |||
Constitutional AI is a method for training AI systems using a set of rules or principles that act as a “constitution” for the AI system. This approach allows the AI system to operate within a societally accepted framework and aligns it with human intentions1. | Constitutional AI is a method for training AI systems using a set of rules or principles that act as a “constitution” for the AI system. This approach allows the AI system to operate within a societally accepted framework and aligns it with human intentions1. | ||
| Line 35: | Line 33: | ||
<img src="https://miro.medium.com/v2/resize:fit:828/format:webp/1*thP_MQQ-pLmZn_s4nsnfeg.png" width="1000"> | <img src="https://miro.medium.com/v2/resize:fit:828/format:webp/1*thP_MQQ-pLmZn_s4nsnfeg.png" width="1000"> | ||
| + | |||
| + | <youtube>5GqtRXY-80k</youtube> | ||
| + | <youtube>i5rzqACykYk</youtube> | ||
| + | <youtube>quyqRIHRa60</youtube> | ||
| + | |||
| + | = Claude | Anthropic = | ||
| + | * [https://www.anthropic.com/ Claude | Anthropic] | ||
| + | ** [https://scale.com/blog/chatgpt-vs-claude#What%20is%20%E2%80%9CConstitutional%20AI%E2%80%9D? Meet Claude: Anthropic’s Rival to ChatGPT | Riley Goodside - Scale] | ||
| + | ** [https://arstechnica.com/information-technology/2023/03/anthropic-introduces-claude-a-more-steerable-ai-competitor-to-chatgpt/ Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT | Benj Edwards - ARS Technica] ... Anthropic aims for "safer" and "less harmful" AI, but at a higher price. | ||
| + | |||
| + | <youtube>KB5r9xmrQBY</youtube> | ||
| + | <youtube>_TAWaueEmoY</youtube> | ||
| + | <youtube>Us-OAs9hDI4</youtube> | ||
Revision as of 14:48, 16 April 2023
YouTube ... Quora ...Google search ...Google News ...Bing News
- Reinforcement Learning (RL)
- Assistants ... Hybrid Assistants ... Agents ... Negotiation ... HuggingGPT ... LangChain
- Generative AI ... Conversational AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's Bing ... You ...Google's Bard ... Baidu's Ernie
- Reinforcement Learning (RL) from Human Feedback (RLHF)
- Paper Review: Constitutional AI, Training LLMs using Principles
Constitutional AI is a method for training AI systems using a set of rules or principles that act as a “constitution” for the AI system. This approach allows the AI system to operate within a societally accepted framework and aligns it with human intentions1.
Some benefits of using Constitutional AI include allowing a model to explain why it is refusing to provide an answer, improving transparency of AI decision making, and controlling AI behavior more precisely with fewer human labels.
The Constitutional AI methodology has two phases, similar to Reinforcement Learning (RL) from Human Feedback (RLHF).
1. The Supervised Learning Phase.
2. The Reinforcement Learning Phase.
Claude | Anthropic
- Claude | Anthropic
- Meet Claude: Anthropic’s Rival to ChatGPT | Riley Goodside - Scale
- Anthropic introduces Claude, a “more steerable” AI competitor to ChatGPT | Benj Edwards - ARS Technica ... Anthropic aims for "safer" and "less harmful" AI, but at a higher price.
