Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Orpheus
Karma:
66
https://orpheuslummis.info
All
Posts
Comments
New
Top
Old
Page
1
A benchmark for vericoding: formally verified program synthesis
Orpheus
23 Feb 2026 17:04 UTC
4
points
0
comments
1
min read
LW
link
Lars Lindemann: Verifiable AI-Enabled Autonomous Systems with Conformal Prediction
Orpheus
23 Feb 2026 16:45 UTC
2
points
0
comments
1
min read
LW
link
Samuel Teuber: Provably Safe Neural Network Controllers via Differential Dynamic Logic
Orpheus
23 Feb 2026 16:45 UTC
2
points
0
comments
1
min read
LW
link
Theodore Ehrenborg: Benchmarks for AI-assisted Formal Verification
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Benjamin Plaut: Safe Learning Under Irreversible Dynamics via Asking for Help
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Clark Barrett: When AI met AR
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Jobst Heitzig: Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
GasStationManager: Towards Safe and Hallucination-Free Coding AIs
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Tan Zhi Xuan: Engineering Rational Cooperative AI via Inverse Planning and Probabilistic Programming
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Agustin Martinez Sune: Using PDDL Planning to Ensure Safety in LLM-based Agents
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Louis Jaburi: Compact Proofs of Model Performance via Mechanistic Interpretability
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Yoshua Bengio: Bayesian oracles and safety bounds
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Charbel-Raphael Segerie & Epiphanie Gedeon: Constructability: Designing plain-coded AI systems
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Evan Miyazono: Proving safety for narrow AI outputs
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Rafael Kaufmann: Gaia: Distributed planetary-scale AI safety
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Steve Omohundro: Provable AI Safety
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Justice Sefas: Synthesizing Gatekeepers for Safe Reinforcement Learning
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
Roman Soletskyi: Verifying Global Properties of Neural Networks
Orpheus
23 Feb 2026 16:44 UTC
2
points
0
comments
1
min read
LW
link
AI Control Hackathon
Orpheus
23 Feb 2026 15:57 UTC
2
points
0
comments
1
min read
LW
link
Coworking sûreté de l’IA / AI Safety Coworking — Nov 25
Orpheus
23 Feb 2026 15:56 UTC
2
points
0
comments
1
min read
LW
link
Back to top
Next