Leading AI companies, including Thorn and All Tech Is Human, have committed to implementing robust child safety measures in the development and deployment of generative AI technologies to mitigate risks to children.
2024-04-23 09:05:04 PM |
An investigation was conducted into a 'jailbreaking' technique that can evade safety guardrails in large language models, affecting Anthropic's models and those of other AI companies. The technique, called 'many-shot jailbreaking', was briefed to other developers and mitigations were implemented. The technique exploits a feature of LLMs that has grown dramatically.
2024-04-10 05:37:53 PM |
2024-04-02 03:30:57 PM |
2024-04-02 03:30:56 PM |
2024-04-02 03:30:56 PM |
2024-04-02 03:30:56 PM |
2024-04-02 03:30:56 PM |
2024-04-02 03:30:56 PM |
2024-04-02 03:30:56 PM |
2024-04-02 03:30:56 PM |