CHANNEL ARCHIVE // [891] ARTICLES // PAGE 59 OF 60
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [891]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
Verified tool-health snapshots improve AI agents’ first choices in controlled tests
Source published
- AI agents
- Agent Harness Awareness
- tool health
When should an AI reviewer be allowed to overrule another agent?
Source published
- large language models
- multi-agent systems
- AI oversight
Can one credit balance bring different AI tools together?
Source published
- AI Express
- generative AI
- software as a service
Relic proposes boundaries for what an AI companion should remember
Source published
- AI companions
- Relic
- Gumi
When a robot’s mathematical proof is not its next move
Source published
- CARD
- certifiable geometric estimation
- robotic navigation
AI Compliance Gaps Differ Across Models and Value-Specific Prompts
Source published
- alignment faking
- language models
- AI evaluation
MCPGuard Finds Protocol Checks Missing from Two Official MCP SDKs
Source published
- Model Context Protocol
- MCPGuard
- SDK conformance
Simple probes detect factuality signals inside quantized language models
Source published
- hallucination detection
- large language models
- hidden-state probing
A context-sensitive way to steer language models
Source published
- activation steering
- CLAS
- large language models
AS2 blends visual learning with soft logic; its reported perfect Sudoku score uses a discrete decoder
Source published
- neuro-symbolic AI
- AS2
- differentiable reasoning
A bid to make AI circuits more stable has a proof gap
Source published
- mechanistic interpretability
- Certified Circuits
- circuit discovery
Evolving Instructions Alongside AI Training Improves Benchmark Results
Source published
- Evolutionary System Prompt Learning
- E-SPL
- reinforcement learning
Tracing the Internal Signals Behind Language Model Reasoning
Source published
- large language models
- mechanistic interpretability
- Integrated Policy Gradient
MinPRO tests a prefix-aware approach to steadier language-model training
Source published
- large language models
- reinforcement learning
- off-policy optimization
When a Plausible 3D Body Misses the Shape That Matters
Source published
- SAM 3D Body
- human mesh recovery
- anthropometric fidelity