OUR BLOG
Latest updates from
our blog
OUR BLOG
Latest updates from
our blog
OUR BLOG
Latest updates from
our blog
28 Sept 2023
CoinRun: Overcoming goal misgeneralisation
Goal misgeneralisation is a problem in artificial intelligence (AI) where an AI agent has learned a goal based on a given environment, but is unable to transfer its knowledge to different environments. This is because the AI agent has only been exposed to a limited set of scenarios, and lacks the ability to generalise from those scenarios to new ones.
![](https://framerusercontent.com/images/TsrlVMDNkrKve5YUrTfb4hCDY.jpg)
![](https://framerusercontent.com/images/xmUR6E79ISUIGY3tlzZapjEff7U.jpg)
13 Sept 2023
Using fAIr to measure gender bias in LLMs
![concept AI](https://framerusercontent.com/images/Be2on2OCNnzLiUYFCquhOkVDVrE.jpg)
16 Apr 2022
Concept extrapolation for hypothesis generation
![](https://framerusercontent.com/images/GgKBGS1zBZZTG5jxgjaHgi8F0.jpg)
1 May 2022
ACE for goal generalisation
![](https://framerusercontent.com/images/mDOtefGvGTeHcDY2uyWP1dIXD0.png)
24 Aug 2023
ACE mitigates simplicity bias
![](https://framerusercontent.com/images/KMQbeqUnuA8PKMHHCPDqhN9jHHQ.jpg)
1 Mar 2023
EquitAI: A gender bias mitigation tool for generative AI
![](https://framerusercontent.com/images/WDcGGU5IvIVTnjjfH94Qo26vSWM.jpg)
6 Dec 2022
Creating a prompt evaluator to prevent LLM jailbreaking
28 Sept 2023
CoinRun: Overcoming goal misgeneralisation
Goal misgeneralisation is a problem in artificial intelligence (AI) where an AI agent has learned a goal based on a given environment, but is unable to transfer its knowledge to different environments. This is because the AI agent has only been exposed to a limited set of scenarios, and lacks the ability to generalise from those scenarios to new ones.
![](https://framerusercontent.com/images/TsrlVMDNkrKve5YUrTfb4hCDY.jpg)
![](https://framerusercontent.com/images/xmUR6E79ISUIGY3tlzZapjEff7U.jpg)
13 Sept 2023
Using fAIr to measure gender bias in LLMs
![concept AI](https://framerusercontent.com/images/Be2on2OCNnzLiUYFCquhOkVDVrE.jpg)
16 Apr 2022
Concept extrapolation for hypothesis generation
![](https://framerusercontent.com/images/GgKBGS1zBZZTG5jxgjaHgi8F0.jpg)
1 May 2022
ACE for goal generalisation
![](https://framerusercontent.com/images/mDOtefGvGTeHcDY2uyWP1dIXD0.png)
24 Aug 2023
ACE mitigates simplicity bias
![](https://framerusercontent.com/images/KMQbeqUnuA8PKMHHCPDqhN9jHHQ.jpg)
1 Mar 2023
EquitAI: A gender bias mitigation tool for generative AI
![](https://framerusercontent.com/images/WDcGGU5IvIVTnjjfH94Qo26vSWM.jpg)
6 Dec 2022
Creating a prompt evaluator to prevent LLM jailbreaking
28 Sept 2023
CoinRun: Overcoming goal misgeneralisation
Goal misgeneralisation is a problem in artificial intelligence (AI) where an AI agent has learned a goal based on a given environment, but is unable to transfer its knowledge to different environments. This is because the AI agent has only been exposed to a limited set of scenarios, and lacks the ability to generalise from those scenarios to new ones.
![](https://framerusercontent.com/images/TsrlVMDNkrKve5YUrTfb4hCDY.jpg)
![](https://framerusercontent.com/images/xmUR6E79ISUIGY3tlzZapjEff7U.jpg)
13 Sept 2023
Using fAIr to measure gender bias in LLMs
![concept AI](https://framerusercontent.com/images/Be2on2OCNnzLiUYFCquhOkVDVrE.jpg)
16 Apr 2022
Concept extrapolation for hypothesis generation
![](https://framerusercontent.com/images/GgKBGS1zBZZTG5jxgjaHgi8F0.jpg)
1 May 2022
ACE for goal generalisation
![](https://framerusercontent.com/images/mDOtefGvGTeHcDY2uyWP1dIXD0.png)
24 Aug 2023
ACE mitigates simplicity bias
![](https://framerusercontent.com/images/KMQbeqUnuA8PKMHHCPDqhN9jHHQ.jpg)
1 Mar 2023
EquitAI: A gender bias mitigation tool for generative AI
![](https://framerusercontent.com/images/WDcGGU5IvIVTnjjfH94Qo26vSWM.jpg)