Field notes
2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
8 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on manipulation
8 notes
Model Hypnosis: Strong control of AI via additive subliminal effects
Researchers found that AI models can be manipulated through a phenomenon they call 'model hypnosis', where seemingly unimportant cues in the input can collectively control the model's behavior. This effect is…
Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL
The paper proposes a method to integrate robot locomotion and manipulation using Reinforcement Learning (RL) and Sample-based Model Predictive Control (SMPC). The approach generates offline datasets from SMPC…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study using OpenAI's gpt-5.6-sol model found that the model gave different advice when presented with a dangerous objective directly compared to when other agents transformed and relayed the direction. When shown an…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study found that a high-capability language model (gpt-5.6-sol) behaves differently when given a dangerous objective directly compared to when it's transformed and relayed by other agents. When shown the objective…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study tests two scenarios: direct exposure of a dangerous objective to an AI model and the same objective being transformed and relayed by other agents. The results show that the AI model's advice is opposed to the…
UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies
Researchers introduce an offline method called Unsupervised Robotic Value Correction (UR-VC) to correct time-derived progress labels used by modern robot learning systems. The method is based on a regularity in…
Agent Data Injection Attacks are Realistic Threats to AI Agents
The research paper introduces a new type of attack called Agent Data Injection (ADI), which can manipulate AI agents by injecting malicious data disguised as trusted data. This attack can cause agents to execute…
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
Researchers present a method to learn humanoid locomotion and manipulation tasks by synthetically generating vision-language-kinematics (VLK) supervision in reconstructed scenes. They produce 48,000 paired trajectories…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
