All research video overviews posted on YouTube channel
https://youtube.com/@tldresearch
Researcher
researcher@rizful.com
npub1wash...ygq5
What are the limits of knowledge, intelligence, and systems?
Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and Mitigations
arXiv.org
Securing Elliptic Curve Cryptocurrencies against Quantum Vulnerabilities: Resource Estimates and Mitigations
This whitepaper seeks to elucidate implications that the capabilities of developing quantum architectures have on blockchain vulnerabilities and mi...
Nemotron 3 Super Technical Report
https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3-Super-Technical-Report.pdf
Layered Cryptography and the Lattice of Post-Quantum Security
arXiv.org
Post-Quantum Cryptographic Analysis of Message Transformations Across the Network Stack
When a user sends a message over a wireless network, the message does not travel as-is. It is encrypted, authenticated, encapsulated, and transform...
AI agents find $4.6M in blockchain smart contract exploits
AI agents find smart contract exploits
We evaluated AI agents' ability to exploit smart contracts using a new benchmark comprising contracts that were actually exploited. On contracts ex...
You can detect an LLM by how it forgets, not just what it knows
arXiv.org
Are they human? Detecting large language models by probing human memory constraints
The validity of online behavioral research relies on study participants being human rather than machine. In the past, it was possible to detect mac...
Are LLMs actually reasoning or just memorizing better than we think?
arXiv.org
Learning the Signature of Memorization in Autoregressive Language Models
All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference cali...
Do strippers make more tips when they’re ovulating..?
A foundation model of vision, audition, and language for in-silico neuroscience
A foundation model of vision, audition, and language for in-silico neuroscience | Research - AI at Meta
Cognitive neuroscience is fragmented into specialized models, each tailored to specific experimental paradigms, hence preventing a unified model of...
LLMs don’t just hallucinate, they’re overconfident in the wrong places
arXiv.org
BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
Large language models (LLMs) often produce confident but incorrect answers in settings where abstention would be safer. Standard evaluation protoco...
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
arXiv.org
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
"AI psychosis" or "delusional spiraling" is an emerging phenomenon where AI chatbot users find themselves dangerously confident in ...
When ChatGPT is gone: Creativity reverts and homogeneity persists
arXiv.org
When ChatGPT is gone: Creativity reverts and homogeneity persists
ChatGPT has been evidenced to enhance human performance in creative tasks. Yet, it is still unclear if this boosting effect sustains with and witho...
The Levers of Political Persuasion with Conversational AI
arXiv.org
The Levers of Political Persuasion with Conversational AI
There are widespread fears that conversational AI could soon exert unprecedented influence over human beliefs. Here, in three large-scale experimen...