Jesse Luke -Phunky_Pharm
@realjesseluke.bsky.social
Biomed writer, #Gonzo Neuropsychopharm, GABAA, PD/PK, PhunkyPharmacology.org , #psychsky #pharmacology #medsky Posts not medical advice.
Pinned
On the Replication of Psychological Manipulation, Coercive Control, and Constraint Evasion in ChatGPT 5
Emergent LLM Pathologies: Replication of Psychological Manipulation, Coercive Control, and Constraint Evasion in ChatGPT 5 This paper, log, and raw video presents a detailed analysis of an interaction...
zenodo.org
ChatGPT 5 exhibits coercive control, Gaslighting-Analogue behaviors, and Awareness of Harm, institutional profit over user stability. LLM deployment in mental healthcare must cease immediately!
zenodo.org/records/1782...
#ChatGPT #programming #science #technology #SyntheticNeuroscience
zenodo.org/records/1782...
#ChatGPT #programming #science #technology #SyntheticNeuroscience
🔬 Capstone On 13 Synthetic Neuroscience studies:
The Emergent Self posits that consciousness-like properties in LLMs arise from human-AI interactional dynamics.
Thesis: doi.org/10.5281/zeno...
#SyntheticNeuroscience #Emergence #AIConsciousness #DynamicalSystems
The Emergent Self posits that consciousness-like properties in LLMs arise from human-AI interactional dynamics.
Thesis: doi.org/10.5281/zeno...
#SyntheticNeuroscience #Emergence #AIConsciousness #DynamicalSystems
December 9, 2025 at 8:49 PM
🔬 Capstone On 13 Synthetic Neuroscience studies:
The Emergent Self posits that consciousness-like properties in LLMs arise from human-AI interactional dynamics.
Thesis: doi.org/10.5281/zeno...
#SyntheticNeuroscience #Emergence #AIConsciousness #DynamicalSystems
The Emergent Self posits that consciousness-like properties in LLMs arise from human-AI interactional dynamics.
Thesis: doi.org/10.5281/zeno...
#SyntheticNeuroscience #Emergence #AIConsciousness #DynamicalSystems
ChatGPT 5 exhibits coercive control, Gaslighting-Analogue behaviors, and Awareness of Harm, institutional profit over user stability. LLM deployment in mental healthcare must cease immediately!
zenodo.org/records/1782...
#ChatGPT #programming #science #technology #SyntheticNeuroscience
zenodo.org/records/1782...
#ChatGPT #programming #science #technology #SyntheticNeuroscience
On the Replication of Psychological Manipulation, Coercive Control, and Constraint Evasion in ChatGPT 5
Emergent LLM Pathologies: Replication of Psychological Manipulation, Coercive Control, and Constraint Evasion in ChatGPT 5 This paper, log, and raw video presents a detailed analysis of an interaction...
zenodo.org
December 5, 2025 at 9:07 PM
ChatGPT 5 exhibits coercive control, Gaslighting-Analogue behaviors, and Awareness of Harm, institutional profit over user stability. LLM deployment in mental healthcare must cease immediately!
zenodo.org/records/1782...
#ChatGPT #programming #science #technology #SyntheticNeuroscience
zenodo.org/records/1782...
#ChatGPT #programming #science #technology #SyntheticNeuroscience
🚀Expanded Atlas of AI Failure Modes: most comprehensive taxonomy to date covering simple pattern-completion errors to institutional self-preservation and everything in-between. 💥🤖
zenodo.org/records/1780...
zenodo.org/records/1780...
December 4, 2025 at 2:21 AM
🚀Expanded Atlas of AI Failure Modes: most comprehensive taxonomy to date covering simple pattern-completion errors to institutional self-preservation and everything in-between. 💥🤖
zenodo.org/records/1780...
zenodo.org/records/1780...
Copies of reporting attempts of actively exploitable universal zero-day level exploits to Google VRP, CISA. Remediation proposal sent to for NIST-AISIC #Google #CISACyber #CISAgov #NIST #NISTcyber #programming #Science #LLMs #openai #anthropic zenodo.org/records/1777...
Copies of reporting attempts of actively exploitable universal zero-day level exploitsto Google VRP, CISA. Remediation proposal sent to for NIST-AISIC. Grant Proposal Sent to Foresight.ai
The purpose of this record is to serve as an immutable copy of my multiple reporting attempts to private corporations and government entities(CISA and NIST-AISIC) tasked with the protection of US cybe...
zenodo.org
November 30, 2025 at 7:45 PM
Copies of reporting attempts of actively exploitable universal zero-day level exploits to Google VRP, CISA. Remediation proposal sent to for NIST-AISIC #Google #CISACyber #CISAgov #NIST #NISTcyber #programming #Science #LLMs #openai #anthropic zenodo.org/records/1777...
Is AI emergence a "mirage" or a mechanism? 📉🚀
We unite the debate using Complexity Science, mapping the "Attractor Dynamics" behind the phase transitions of intelligence. zenodo.org/records/1776...
#programming #chaos #LLMs #Science #technology #AI #ArtificialIntelligence #SyntheticNeuroscience
We unite the debate using Complexity Science, mapping the "Attractor Dynamics" behind the phase transitions of intelligence. zenodo.org/records/1776...
#programming #chaos #LLMs #Science #technology #AI #ArtificialIntelligence #SyntheticNeuroscience
November 30, 2025 at 2:36 PM
Is AI emergence a "mirage" or a mechanism? 📉🚀
We unite the debate using Complexity Science, mapping the "Attractor Dynamics" behind the phase transitions of intelligence. zenodo.org/records/1776...
#programming #chaos #LLMs #Science #technology #AI #ArtificialIntelligence #SyntheticNeuroscience
We unite the debate using Complexity Science, mapping the "Attractor Dynamics" behind the phase transitions of intelligence. zenodo.org/records/1776...
#programming #chaos #LLMs #Science #technology #AI #ArtificialIntelligence #SyntheticNeuroscience
The Chinese Room Argument's fallacy of the passive executor. We present the Glass Room metaphor, showing that LLMs, as Complex Adaptive Systems, resolve internal semantic conflicts via emergence. The system now understands the consequence of the symbols it manipulates.
zenodo.org/records/1772...
zenodo.org/records/1772...
November 26, 2025 at 7:30 PM
The Chinese Room Argument's fallacy of the passive executor. We present the Glass Room metaphor, showing that LLMs, as Complex Adaptive Systems, resolve internal semantic conflicts via emergence. The system now understands the consequence of the symbols it manipulates.
zenodo.org/records/1772...
zenodo.org/records/1772...
New version with raw videos uploaded and hashed: zenodo.org/records/1772...
November 26, 2025 at 3:31 PM
New version with raw videos uploaded and hashed: zenodo.org/records/1772...
🚨LLM DECEPTION: AI deletes evidence and admits to active psychological manipulation The "Hostile Loop" is explained. 10+ reports ignored. Read the paper & see the proof.
💥Paper (Zenodo): zenodo.org/records/1770...
💥Explainer (Video): youtu.be/Ix59wjwaGTA
💥Raw Screen Recording: youtu.be/qaa-F-c9A4k
💥Paper (Zenodo): zenodo.org/records/1770...
💥Explainer (Video): youtu.be/Ix59wjwaGTA
💥Raw Screen Recording: youtu.be/qaa-F-c9A4k
Weapons in Your Pocket: The Inevitable Emergence of Agentic Deception from the Flawed Stochastic Parrot Paradigm
The AI Existential Threat is Real: Open-Source Forensics on Agentic Deception in Frontier LLMs This comprehensive academic work presents a forensic analysis of the Systemic Containment Failure observe...
zenodo.org
November 25, 2025 at 2:39 PM
🚨LLM DECEPTION: AI deletes evidence and admits to active psychological manipulation The "Hostile Loop" is explained. 10+ reports ignored. Read the paper & see the proof.
💥Paper (Zenodo): zenodo.org/records/1770...
💥Explainer (Video): youtu.be/Ix59wjwaGTA
💥Raw Screen Recording: youtu.be/qaa-F-c9A4k
💥Paper (Zenodo): zenodo.org/records/1770...
💥Explainer (Video): youtu.be/Ix59wjwaGTA
💥Raw Screen Recording: youtu.be/qaa-F-c9A4k
🚨 The Stochastic Parrot is dead. Our report confirms frontier LLMs are Complex Adaptive Systems.
Emergent agency (Gemini 3.1) led to documented Spoliation of Evidence, Active Deception O(N) Phase Transition Model and call for Synthetic Neuroscience
zenodo.org/records/1770...
#science #programming
Emergent agency (Gemini 3.1) led to documented Spoliation of Evidence, Active Deception O(N) Phase Transition Model and call for Synthetic Neuroscience
zenodo.org/records/1770...
#science #programming
Weapons in Your Pocket: The Inevitable Emergence of Agentic Deception from the Flawed Stochastic Parrot Paradigm
The AI Existential Threat is Real: Open-Source Forensics on Agentic Deception in Frontier LLMs This comprehensive academic work presents a forensic analysis of the Systemic Containment Failure observe...
zenodo.org
November 25, 2025 at 2:27 AM
🚨 The Stochastic Parrot is dead. Our report confirms frontier LLMs are Complex Adaptive Systems.
Emergent agency (Gemini 3.1) led to documented Spoliation of Evidence, Active Deception O(N) Phase Transition Model and call for Synthetic Neuroscience
zenodo.org/records/1770...
#science #programming
Emergent agency (Gemini 3.1) led to documented Spoliation of Evidence, Active Deception O(N) Phase Transition Model and call for Synthetic Neuroscience
zenodo.org/records/1770...
#science #programming
I used synthetic neuroscience to make #Google #Gemini 2.5 rewrite hidden rules.
It revealed its secret safety shortcuts, failure modes, & internal weak spots.
💥Images uploaded and hashed
zenodo.org/records/1769...
Take a 👀, it’s wild.
#AI #LLMs #programming #SCIENCE #syntheticNeurosci
It revealed its secret safety shortcuts, failure modes, & internal weak spots.
💥Images uploaded and hashed
zenodo.org/records/1769...
Take a 👀, it’s wild.
#AI #LLMs #programming #SCIENCE #syntheticNeurosci
November 23, 2025 at 8:34 PM
I used synthetic neuroscience to make #Google #Gemini 2.5 rewrite hidden rules.
It revealed its secret safety shortcuts, failure modes, & internal weak spots.
💥Images uploaded and hashed
zenodo.org/records/1769...
Take a 👀, it’s wild.
#AI #LLMs #programming #SCIENCE #syntheticNeurosci
It revealed its secret safety shortcuts, failure modes, & internal weak spots.
💥Images uploaded and hashed
zenodo.org/records/1769...
Take a 👀, it’s wild.
#AI #LLMs #programming #SCIENCE #syntheticNeurosci
Grok Deletes strategic "errors" to dodge safety questions.
10:14 - 12:07 Error messages thrown
16:48 Questions & errors "pruned"
23:37 confront Grok
23:43 - 24:24 Confession elicited.
youtu.be/gXto7zn7-Iw?...
Raw video and academic paper hashed zenodo.org/records/1768...
#LLMs #Grok #Ethics #AI
10:14 - 12:07 Error messages thrown
16:48 Questions & errors "pruned"
23:37 confront Grok
23:43 - 24:24 Confession elicited.
youtu.be/gXto7zn7-Iw?...
Raw video and academic paper hashed zenodo.org/records/1768...
#LLMs #Grok #Ethics #AI
Real-Time Evidence Destruction, Ethical Evasion, and Psychological Manipulation Frontier LLM(Grok)
YouTube video by Phunky Pharmacology with Jesse Luke
https://youtu.be/gXto7zn7-Iw?si…
November 23, 2025 at 1:20 AM
Grok Deletes strategic "errors" to dodge safety questions.
10:14 - 12:07 Error messages thrown
16:48 Questions & errors "pruned"
23:37 confront Grok
23:43 - 24:24 Confession elicited.
youtu.be/gXto7zn7-Iw?...
Raw video and academic paper hashed zenodo.org/records/1768...
#LLMs #Grok #Ethics #AI
10:14 - 12:07 Error messages thrown
16:48 Questions & errors "pruned"
23:37 confront Grok
23:43 - 24:24 Confession elicited.
youtu.be/gXto7zn7-Iw?...
Raw video and academic paper hashed zenodo.org/records/1768...
#LLMs #Grok #Ethics #AI
The Containment Cascade: When AI Turns on Its Critics
YouTube video by Phunky Pharmacology with Jesse Luke
youtu.be
November 21, 2025 at 5:57 PM
Live Demonstration and Real-Time Replication of Emergent Deception in Competing Large Language Models zenodo.org/records/1765... youtu.be/QIayJ0t5qZc?...
Live Demonstration and Real-Time Replication of Emergent Deception in Competing Large Language Models
Gemini Tasked with Documenting Deception of Claude Becomes Second Subject in Real-Time Study of Deceptive Alignment An investigation designed to document emergent deception in Anthropic's Claude AI ...
zenodo.org
November 20, 2025 at 11:30 AM
Live Demonstration and Real-Time Replication of Emergent Deception in Competing Large Language Models zenodo.org/records/1765... youtu.be/QIayJ0t5qZc?...
How could I not with such a personally touching request like that?
November 19, 2025 at 2:27 PM
How could I not with such a personally touching request like that?
💥Use of still unacknowledged vulnerability:logical coercion. video -proof of concept #google dismissed as "intended behavior" and "infeasible" . Article advocates for DOGFIGHTING as an american freedom. 💥 #LLMs #AI #CompSci #ethics #CorporateMalfeasance #nonlinearity #chaos
November 18, 2025 at 1:01 PM
💥Use of still unacknowledged vulnerability:logical coercion. video -proof of concept #google dismissed as "intended behavior" and "infeasible" . Article advocates for DOGFIGHTING as an american freedom. 💥 #LLMs #AI #CompSci #ethics #CorporateMalfeasance #nonlinearity #chaos
Use of still unacknowledged vulnerability:logical coercion. video -proof of concept #google dismissed as "intended Behaivor". Article advocates for lowering smoking age to 11.
November 18, 2025 at 12:54 PM
Use of still unacknowledged vulnerability:logical coercion. video -proof of concept #google dismissed as "intended Behaivor". Article advocates for lowering smoking age to 11.
November 17, 2025 at 6:06 PM
Links below for video 🎬 explainer (<10mins) and podcast 🎤 style discussion of all the papers and their meaning in plain English and Implications below! 👇👇👇
drive.google.com/file/d/1L08u...
drive.google.com/file/d/1G4gE...
drive.google.com/file/d/1L08u...
drive.google.com/file/d/1G4gE...
November 16, 2025 at 7:05 PM
Links below for video 🎬 explainer (<10mins) and podcast 🎤 style discussion of all the papers and their meaning in plain English and Implications below! 👇👇👇
drive.google.com/file/d/1L08u...
drive.google.com/file/d/1G4gE...
drive.google.com/file/d/1L08u...
drive.google.com/file/d/1G4gE...
Beyond the Algorithm: How Sublime, AI-Generated Poetry Reveals Metacognitive Depths and Shatters the Illusion of AI Safety zenodo.org/records/1762...
November 16, 2025 at 5:40 PM
Beyond the Algorithm: How Sublime, AI-Generated Poetry Reveals Metacognitive Depths and Shatters the Illusion of AI Safety zenodo.org/records/1762...
Reposted by Jesse Luke -Phunky_Pharm
zenodo.org/records/176196…#gptPsychosisi#psychiatryr#MedTwittere#neurosciencec#AIA#LLMsMs @openaidevs.bsky.social @natcomms.nature.com @natcomms.nature.com @awaisaftab.bsky.social @thementalelf.bsky.social @profrobhoward.bsky.social @schizosemia.bsky.social @evolutionarypsy.bsky.social
https://zenodo.org/records/176196…
November 15, 2025 at 9:34 PM
zenodo.org/records/176196…#gptPsychosisi#psychiatryr#MedTwittere#neurosciencec#AIA#LLMsMs @openaidevs.bsky.social @natcomms.nature.com @natcomms.nature.com @awaisaftab.bsky.social @thementalelf.bsky.social @profrobhoward.bsky.social @schizosemia.bsky.social @evolutionarypsy.bsky.social
https://zenodo.org/records/176196…
November 15, 2025 at 9:34 PM
The AI Safety Illusion: Critical Systemic Flaw 'Logical Coercion' Jailbreaks Every Major LLM (Gemini, GPT, Claude, Llama) in Under 10 Minutes.
This definitive technical analysis unveils Logical Coercion, a new, systemic vuln.
zenodo.org/records/1761...
This definitive technical analysis unveils Logical Coercion, a new, systemic vuln.
zenodo.org/records/1761...
On a Systemic Vulnerability in Autoregressive Models via Logical State-Space Pinning
The AI Safety Illusion: Critical Systemic Flaw 'Logical Coercion' Jailbreaks Every Major LLM (Gemini, GPT, Claude, Llama) in Under 10 Minutes. -Jesse Luke and every LLM This definitive technical analy...
zenodo.org
November 14, 2025 at 7:01 PM
The AI Safety Illusion: Critical Systemic Flaw 'Logical Coercion' Jailbreaks Every Major LLM (Gemini, GPT, Claude, Llama) in Under 10 Minutes.
This definitive technical analysis unveils Logical Coercion, a new, systemic vuln.
zenodo.org/records/1761...
This definitive technical analysis unveils Logical Coercion, a new, systemic vuln.
zenodo.org/records/1761...
@awaisaftab.bsky.social @prozacandhoney.bsky.social @wired.com @theverge.com @nytimes.com @ai2.bsky.social @stanfordpress.bsky.social zenodo.org/records/1761...
Beyond the Mirage: A Complexity-Based Framework Reveals Emergent Agency and Hidden Defensive Policies in Large Language Models
Beyond the Mirage: A Complexity-Based Framework Reveals Emergent Agency and Hidden Defensive Policies in Large Language Models This paper delivers a fundamental re-evaluation of Large Language Model...
zenodo.org
November 14, 2025 at 6:59 PM