When an outsider red-teams an #LLM without internal access using only language to probe its logic, emotion, and control it’s not hacking; it’s precision systems research.
Full study → medium.com/p/4401ccdf2814
#RedTeaming #CognitiveAI #NeuroAI #AIResearch #AGI #EthicalAI #GPT5 #Gemini #RLHF #Grok
Full study → medium.com/p/4401ccdf2814
#RedTeaming #CognitiveAI #NeuroAI #AIResearch #AGI #EthicalAI #GPT5 #Gemini #RLHF #Grok
Testing Cognitive Resonance in Large Language Models: A Red Teaming Study on Self-Referential…
Exploring paradoxical commands, metaphorical infiltration, and synthetic emotional regulation under the TONE-μ protocol
medium.com
October 18, 2025 at 12:12 AM
Everybody can reply
While LLMs can solve complex problems and generate novel outputs, their foundational mechanism is statistical. This sparks debate on whether such sophisticated imitation constitutes genuine reasoning or just advanced pattern recognition. 🤔 #CognitiveAI 6/6
October 5, 2025 at 1:00 PM
Everybody can reply
The 'g factor' – general intelligence – was a hot topic. Does excelling at one AI task imply broader cognitive strength? Debaters pondered if a single 'g' exists for AI, reflecting overall problem-solving capacity across diverse tasks. #CognitiveAI 3/6
August 18, 2025 at 10:15 AM
Everybody can reply
While LLMs summarize well, their "reflection" often lacks the creative synthesis or deep contextual understanding found in human analysis. True critical thought and novel insights remain a distinct human advantage. #CognitiveAI 5/6
August 17, 2025 at 7:05 AM
Everybody can reply
🌌 AI isn't just transforming what we build it's reshaping how we think. From decision-making to creativity, machines are becoming co-pilots in human cognition. But as we offload thinking, are we upgrading ourselves / outsourcing too much? 🤔💡
#CognitiveAI #Human #AIethics #BlueskyTech #FutureThinking
#CognitiveAI #Human #AIethics #BlueskyTech #FutureThinking
August 1, 2025 at 2:58 PM
Everybody can reply
1 likes
Huge thanks to my co-authors
@boknilev @GabiStanovsky!
Preprint: arxiv.org/abs/2507.07186
Webpage: itay1itzhak.github.io/planted-in-...
We’d love your thoughts, critiques, and ideas 📬
Let’s talk about building more interpretable and trustworthy LLMs!
#NLProc #Bias #CognitiveAI
@boknilev @GabiStanovsky!
Preprint: arxiv.org/abs/2507.07186
Webpage: itay1itzhak.github.io/planted-in-...
We’d love your thoughts, critiques, and ideas 📬
Let’s talk about building more interpretable and trustworthy LLMs!
#NLProc #Bias #CognitiveAI
Planted in Pretraining, Swayed by Finetuning: A Case Study on the...
Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across...
arxiv.org
July 15, 2025 at 1:38 PM
Everybody can reply
This rapid, often surprising trajectory signifies a transformative era. It necessitates a dual strategy: courageous exploration of potential alongside rigorous caution and societal dialogue regarding its integration and implications. #AI #Acceleration #CognitiveAI #AI_Ethics #TuringTest #Sunchaser
May 25, 2025 at 8:51 AM
Everybody can reply
🚀 Paper in progress.
🧪 Code coming soon on GitHub.
🔗 Follow me for updates.
👀 Tagging @DeepMind, @MetaAI, @openai — this is a step toward grounded lifelong learning.
#AGI #CognitiveAI #OpenSource
🧪 Code coming soon on GitHub.
🔗 Follow me for updates.
👀 Tagging @DeepMind, @MetaAI, @openai — this is a step toward grounded lifelong learning.
#AGI #CognitiveAI #OpenSource
May 23, 2025 at 8:52 PM
Everybody can reply
2 likes
Finding truth in AI: Why Partsol chose Ireland - #Podcast Ep 249: Cognitive AI pioneer Dr Darryl Williams explains why Partsol is creating 60 jobs in Dublin and how he plans to upset the GenAI applecart
#ai #genai #cognitiveai #jobs #dublin #tech #podcasts
www.thinkbusiness.ie/articles/ai-...
#ai #genai #cognitiveai #jobs #dublin #tech #podcasts
www.thinkbusiness.ie/articles/ai-...
Trust in AI: Why Partsol chose Ireland | ThinkBusiness
Podcast Ep 249: Cognitive AI pioneer Dr Darryl Williams explains why Partsol is creating 60 jobs in Dublin and how he plans to upset the GenAI applecart.
www.thinkbusiness.ie
April 30, 2025 at 11:59 AM
Everybody can reply
February 16, 2025 at 9:57 PM
Everybody can reply
AI is changing the way we think
#Tech #AI #ChatGPT #AIAlgorithms #System0 #CognitiveAI #HumanAgency #DecisionMaking #Personalization #Autonomy #ArtificialIntelligence #EthicsInAI #TechResearch #Thinking #HumanThinking #Neuroscience
the-14.com/ai-is-changi...
#Tech #AI #ChatGPT #AIAlgorithms #System0 #CognitiveAI #HumanAgency #DecisionMaking #Personalization #Autonomy #ArtificialIntelligence #EthicsInAI #TechResearch #Thinking #HumanThinking #Neuroscience
the-14.com/ai-is-changi...
AI is changing the way we think | The-14
New research shows how “System 0,” a cognitive AI layer, extends human decision-making, yet personalization may limit autonomy by subtly shaping user choices.
the-14.com
November 14, 2024 at 4:05 AM
Everybody can reply
1 likes
🤖 AI hallucinations: A hidden key to Cognitive AI? 🗝️ Explore how machines learn by analogy like humans. 🧠
📚 Personalized education & healthcare await! 🌍🏆 Your thoughts? 🤔
🍃 #CognitiveAI #AIInnovation #FutureTech 🌐 go.digitalengineer.io/PK
📚 Personalized education & healthcare await! 🌍🏆 Your thoughts? 🤔
🍃 #CognitiveAI #AIInnovation #FutureTech 🌐 go.digitalengineer.io/PK
fastcompany.com
go.digitalengineer.io
September 1, 2023 at 10:45 PM
Everybody can reply