OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection

This week, OpenAI published details of GPT-Red, an internal-only automated red-teaming model. Its job is to attack OpenAI’s own models and find prompt injection vulnerabilities. OpenAI gives two reasons. Human red-teaming is time-intensive and does not scale. Commonly used robustness evaluations are already saturated by its latest models. Meanwhile, the attack surface grows. Agents read…

Read Full News

Is $2K Next for ETH After Reclaiming Key Support?

Ethereum has had a notable recovery from its June lows, reclaiming an important resistance zone while testing a major descending trendline on the higher timeframe. Although the latest rally has strengthened short-term sentiment, ETH is still approaching a cluster of technical barriers that could determine whether the recovery extends above $2K or transitions into another…

Read Full News