RSS

Orpheus

Karma: 66

https://​​orpheuslummis.info

A bench­mark for veri­cod­ing: for­mally ver­ified pro­gram synthesis

Orpheus23 Feb 2026 17:04 UTC
4 points
0 comments1 min readLW link

Lars Lin­de­mann: Ver­ifi­able AI-En­abled Au­tonomous Sys­tems with Con­for­mal Prediction

Orpheus23 Feb 2026 16:45 UTC
2 points
0 comments1 min readLW link

Sa­muel Teu­ber: Prov­ably Safe Neu­ral Net­work Con­trol­lers via Differ­en­tial Dy­namic Logic

Orpheus23 Feb 2026 16:45 UTC
2 points
0 comments1 min readLW link

Theodore Ehren­borg: Bench­marks for AI-as­sisted For­mal Verification

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Ben­jamin Plaut: Safe Learn­ing Un­der Ir­re­versible Dy­nam­ics via Ask­ing for Help

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Clark Bar­rett: When AI met AR

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Jobst Heitzig: Model-Based Soft Max­i­miza­tion of Suitable Met­rics of Long-Term Hu­man Power

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

GasS­ta­tionMan­ager: Towards Safe and Hal­lu­ci­na­tion-Free Cod­ing AIs

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Tan Zhi Xuan: Eng­ineer­ing Ra­tional Co­op­er­a­tive AI via In­verse Plan­ning and Prob­a­bil­is­tic Programming

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Agustin Martinez Sune: Us­ing PDDL Plan­ning to En­sure Safety in LLM-based Agents

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Louis Jaburi: Com­pact Proofs of Model Perfor­mance via Mechanis­tic Interpretability

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Yoshua Ben­gio: Bayesian or­a­cles and safety bounds

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Char­bel-Raphael Segerie & Epiphanie Gedeon: Con­structabil­ity: De­sign­ing plain-coded AI systems

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Evan Miya­zono: Prov­ing safety for nar­row AI outputs

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Ra­fael Kauf­mann: Gaia: Distributed plane­tary-scale AI safety

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Steve Omo­hun­dro: Prov­able AI Safety

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Jus­tice Se­fas: Syn­the­siz­ing Gate­keep­ers for Safe Re­in­force­ment Learning

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

Ro­man So­let­skyi: Ver­ify­ing Global Prop­er­ties of Neu­ral Networks

Orpheus23 Feb 2026 16:44 UTC
2 points
0 comments1 min readLW link

AI Con­trol Hackathon

Orpheus23 Feb 2026 15:57 UTC
2 points
0 comments1 min readLW link

Cowork­ing sûreté de l’IA /​ AI Safety Cowork­ing — Nov 25

Orpheus23 Feb 2026 15:56 UTC
2 points
0 comments1 min readLW link