2025-12-23
Things change so quickly! About a year ago, we published work on Advancing Red Teaming with People and AI, https://openai.com/.... Today's blog post puts that into practice, a peek into how we thought about prompt injections for ChatGPT Atlas: https://openai.com/...
TechCrunch
OpenAI details efforts to secure its ChatGPT Atlas browser against prompt injection attacks, including building an “LLM-based automated attacker”
Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections …
2023-09-26
We've included a system card focused on the vision capabilities, building on the work from the GPT-4 system card. Thank you to all our expert testers and red teamers for helping to inform this work! https://openai.com/...
The Verge
OpenAI updates ChatGPT Plus and ChatGPT Enterprise to let users prompt the tool using voice commands or by uploading an image, coming to all users “soon after”
and Look Into Your Life Kyle Wiggers / TechCrunch : OpenAI's GPT-4 with vision still has flaws, paper reveals The Hill : ChatGPT given the ability to talk Laurent Giret / Thurrott ...
2023-09-20
I'm so fortunate to be able to lead this work at OpenAI - and my priority is increasing the diversity in domains, geographies, language representation, and lived experiences of those who we invite to test our systems and shape our mitigations. Please apply!
TechCrunch
OpenAI launches the OpenAI Red Teaming Network, a contracted group of experts to help inform the company's AI model risk assessment and mitigation strategies
Kyle Wiggers / TechCrunch :
Importantly, expert doesn't mean having a fancy qualification. To me, it means having experience in area that is relevant to how people experience or use AI systems. That can be a cultural context, being a parent to a child who you help with homework regularly, or something else!
TechCrunch
OpenAI launches the OpenAI Red Teaming Network, a contracted group of experts to help inform the company's AI model risk assessment and mitigation strategies
Kyle Wiggers / TechCrunch :
2022-06-04
Chatted with @Kantrowitz yesterday about the complicated considerations around bias and representation in DALL-E 2 https://twitter.com/...
Big Technology
Dall-E 2 created 3M images since April and OpenAI is adding up to 1,000 users per week, applying a content policy to try to avoid sensitive or biased images
Alex Kantrowitz / Big Technology : Tweets: @chrisbrogan , @martinsfp , @jon_gluck , @_lamaahmad , @cebsilver , and @kantrowitz Tweets: @chrisbrogan : I want access to this. THIS i...