CHANNEL ARCHIVE // [522] ARTICLES // PAGE 30 OF 35
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [522]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
WAR-CRAFT audits API recommendations against application requirements
Source published
- Web API recommendation
- WAR-CRAFT
- requirement auditing
Four equations summarize changes in sleep across 1,106 nights
Source published
- sleep architecture
- sleep cycles
- symbolic regression
An AI committee can repeat a discussion exactly and still be sensitive to change
Source published
- large language models
- multi-agent deliberation
- deterministic decoding
Skill++: Helping AI agents find the right skills as their libraries grow
Source published
- Skill++
- AI agents
- skill routing
Can Rebuilding a Conversation Help an AI Let Go of Earlier Mistakes?
Source published
- large language models
- multi-turn conversations
- context pollution
When Can Fast Decision Models Replace AI Judges?
Source published
- LLM-as-a-judge
- System-1 decision models
- Jev
A way to spot the risky tail of AI-generated system rules
Source published
- large language models
- heuristic synthesis
- TAILOR
When Answer Order Changes an AI Decision
Source published
- System One decision models
- demographic bias
- AI auditing
Estimating AI Reliability With Fewer Repeated Trials
Source published
- AI evaluation
- Beta mixtures
- repeated sampling
Compressing Small Language Models: When Combining Techniques Helps—and When It Fails
Source published
- small language models
- model compression
- quantization
Exo lets AI agents rewrite their harness while working
Source published
- Exo
- AI agents
- agent harnesses
Medical AI scores fall sharply when answer choices disappear
Source published
- medical AI
- large language models
- medical question answering
Can Matching Score Distributions Bring AI Judges Closer to Human Ratings?
Source published
- LLM-as-a-judge
- streaming quantile matching
- score calibration
A framework for human–AI teamwork that accounts for how advice changes decisions
Source published
- human–AI collaboration
- collaborative omnimechanism design
- outcome indistinguishability
A Transformer’s Arithmetic Circuit Works Despite Local Geometric Distortion
Source published
- mechanistic interpretability
- modular addition
- transformer circuits