Reader

OpenAI Releases GPT-4o mini Model with Improved Jailbreak Resistance

| InfoQ | Default

OpenAI released GPT-4o mini, a smaller version of their flagship GPT-4o model. GPT-4o mini outperforms GPT-3.5 Turbo on several LLM benchmarks and is OpenAI's first model trained with an instruction hierarchy method that improves the model's resistance to jailbreaks and system prompt extraction.

By Anthony Alford