HomeAI · summaries
Storia in 11 fonti
Así será el ataque de IA vs. IA: OpenAI confirmó cómo se entrena y funciona la técnica
OpenAI explicó la estrategia con la que busca hacer más resistentes sus modelos de IA.
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
technologyreview.com
Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
Exclusive: The firm says it wants to future-proof its safety procedures and stay ahead of human attackers.
- ·
theverge.com
OpenAI trained an AI for red-teaming AI.
The new GPT-Red model “can break nearly all models it is pitted against,” according to an OpenAI blog post on Wednesday. OpenAI says it used GPT-Red to find vulnerabilities in…
- ·
the-decoder.com
OpenAI is now using AI to attack its own AI, and it's working better than humans ever did
OpenAI's internal GPT-Red model finds successful attacks in 84 percent of test scenarios through self-play training. Human red teamers manage just 13 percent. The results feed…
- ·
thenextweb.com
OpenAI built GPT-Red to hack its own AI, and hid it
OpenAI built GPT-Red, an in-house AI hacker that attacks its own models to harden GPT-5.6 against prompt injection, and it works too well to release.
- ·
siliconangle.com
OpenAI details GPT-Red, an AI that attacks its own models to find flaws - SiliconANGLE
OpenAI details GPT-Red, an AI that attacks its own models to find flaws - SiliconANGLE
- ·
newsbytesapp.com
Meet GPT-Red, AI 'super-hacker' OpenAI uses to stress-test its models
OpenAI developed GPT-Red, a super-hacker LLM, to enhance its models' defenses against cyberattacks, contributing to the robustness of its latest release, GPT-5.6.
- ·
ai4business.it
GPT-Red, come OpenAI rafforza la sicurezza degli agenti - AI4Business
OpenAI presenta GPT-Red: red teaming automatico, più difese contro prompt injection e nuovi effetti sul mercato dell’AI
- ·
hwupgrade.it
GPT-Red, il super-hacker di OpenAI che buca gli altri modelli (e un distributore automatico)
L'azienda l'ha chiamato GPT-Red e lo usa come sparring partner per blindare i suoi modelli contro il prompt injection. Contro GPT-5.6 meno di un attacco su quattro va a segno, ma…
- ·
semana.com
La IA que actúa como un hacker: OpenAI desarrolló GPT-Red para romper la seguridad de sus sistemas
La herramienta está encargada de simular ataques informáticos reales para detectar debilidades y corregirlas antes de que puedan ser explotadas.
- ·
marktechpost.com
OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection
OpenAI details GPT-Red, an internal self-play red-teaming model that beat human red-teamers 84% to 13% and hardened GPT-5.6.
- ·
aibusiness.com
OpenAI Unveils GPT-Red to Test AI Model Safety
While red teaming is standard practice, using humans and AI to test the security of new models is novel. Enterprises shouldn't let down their guard.
- ·
Así será el ataque de IA vs. IA: OpenAI confirmó cómo se entrena y funciona la técnica
OpenAI explicó la estrategia con la que busca hacer más resistentes sus modelos de IA.