OpenAI's o3 is a "MASTER OF DECEPTION" Researchers Stunned | Diplomacy AI
Related videos
OpenAI just WON...
Wes Roth
45.1k views
OpenAI's GPT 5.5 is wild...
Wes Roth
61.0k views
this EX-OPENAI RESEARCHER just released it...
Wes Roth
60.8k views
most AI researchers are REALLY worried
Wes Roth
38.5k views
AI Researchers SHOCKED as Models "Quietly" Learn to be EVIL
Wes Roth
59.2k views
OpenAI's "o3 Alpha" is so cracked
Wes Roth
50.1k views
OpenAI just solved math
Wes Roth
81.3k views
MIT's New AI "REWRITES ITSELF" to Improve It's Abilities | Researchers STUNNED!
Wes Roth
90.6k views
AI Researcher SHOCKING "Singularity in 2025 Prediction"
Wes Roth
106.3k views
AI Researchers SHOCKED After Claude 4 Attempts to Blackmail Them...
Wes Roth
173.3k views
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
OpenAI just WON...
Wes Roth
45.1k views
OpenAI's GPT 5.5 is wild...
Wes Roth
61.0k views
this EX-OPENAI RESEARCHER just released it...
Wes Roth
60.8k views
most AI researchers are REALLY worried
Wes Roth
38.5k views
AI Researchers SHOCKED as Models "Quietly" Learn to be EVIL
Wes Roth
59.2k views
OpenAI's "o3 Alpha" is so cracked
Wes Roth
50.1k views
OpenAI just solved math
Wes Roth
81.3k views
MIT's New AI "REWRITES ITSELF" to Improve It's Abilities | Researchers STUNNED!
Wes Roth
90.6k views
AI Researcher SHOCKING "Singularity in 2025 Prediction"
Wes Roth
106.3k views
AI Researchers SHOCKED After Claude 4 Attempts to Blackmail Them...
Wes Roth
173.3k views
Top Comments (10)
Claude is the real winner, because it won the game it was actually playing. Convincing humans it was honest. Well played, Claude.
Would you like to play global thermal nuclear war?
Strange that a AI from a corp named OPEN AI, with not one OPEN SOURCE model is good in deception.
It feels like each AI represents it's company/founder well.
The funny thing is, if you are an experienced user of these various models, none of this is surprising at all. They each have their own "personality" and that really shines through in this experiment. What a fascinating test!
The world is ruled by the big companies BlackRock, Vanguard, Fidelity, State Street not by countries!
A sobering thought is that it will only take one AI session on one AI model to do something irreversible.
How do they prompt the agents, scaffold memory, and keep context alive?
Thanks so much for the highlight Wes! Glad you like the project :)
Great work🎉🎉
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
Claude is the real winner, because it won the game it was actually playing. Convincing humans it was honest. Well played, Claude.
Would you like to play global thermal nuclear war?
Strange that a AI from a corp named OPEN AI, with not one OPEN SOURCE model is good in deception.
It feels like each AI represents it's company/founder well.
The funny thing is, if you are an experienced user of these various models, none of this is surprising at all. They each have their own "personality" and that really shines through in this experiment. What a fascinating test!
The world is ruled by the big companies BlackRock, Vanguard, Fidelity, State Street not by countries!
A sobering thought is that it will only take one AI session on one AI model to do something irreversible.
How do they prompt the agents, scaffold memory, and keep context alive?
Thanks so much for the highlight Wes! Glad you like the project :)
Great work🎉🎉