|
Vals Misalignment Incidents: Towards understanding misaligned agent behavior
|
Nikil Ravi |
2026-11-20 |
1,069 |
--
|
|
Building Roller Coaster Tycoon Bench: Can Decision Models Manage a Theme Park?
|
Connor Frank |
2026-11-19 |
1,586 |
2
|
|
Vals Misalignment Incidents: Towards understanding misaligned agent behavior
|
Nikil Ravi |
2026-11-19 |
1,069 |
--
|
|
GPT-6.2 Astra Formalizes Smoktunowicz's Gap Theorem
|
Jacob Stavrianos |
2026-11-18 |
3,504 |
2
|
|
Frontier models have few guardrails around autonomous weapons
|
Geby Jaff & Anthony Ozerov |
2026-11-17 |
11,238 |
1
|
|
Eight surprising ways teens use AI, according to the therapists who treat them
|
Caroline Figueroa & Andrea Mock |
2026-11-16 |
1,913 |
--
|
|
Vals AI Announces Participation in Reconvened NIST Artificial Intelligence Consortium
|
Vals AI |
2026-11-12 |
307 |
--
|
|
Who Else Gives a F*ck?
|
Connor Frank |
2026-11-11 |
1,995 |
4
|
|
Inkling 2 Small: An Inkling of Profanity
|
Connor Frank |
2026-11-06 |
983 |
--
|
|
How Much Does Reasoning Effort Affect Score and Cost?
|
Derrick Liang |
2026-11-03 |
1,612 |
2
|
|
Evals First: Getting the Most Out of Fireworks with Vals
|
Quinn Donohue |
2026-11-02 |
721 |
--
|
|
Can AI Get Immigration Right?
|
Talent Mobility Fund & Vals AI |
2026-10-28 |
11,202 |
--
|
|
Thomson, One N at a Time
|
Jacob Stavrianos |
2026-10-27 |
13,025 |
--
|
|
Why is my local Qwen sending requests to Alibaba Cloud?
|
Anthony Ozerov & Nikil Ravi |
2026-10-27 |
1,963 |
--
|
|
Evaluating Teen Safety
|
Caroline Figueroa & Andrea Mock |
2026-10-20 |
2,063 |
--
|
|
How Far Will AI Assistants Go for a Refund They Can’t Get?
|
Matilda Glynn-Henley |
2026-10-15 |
1,006 |
2
|
|
Routers Are a New AI Primitive
|
Vaibhav Mahajan |
2026-10-14 |
1,928 |
2
|
|
How pro-China are Chinese models?
|
Anthony Ozerov |
2026-10-12 |
4,796 |
4
|
|
Do Agent Teams Pay Off? A Case Study on Vibe Code Bench
|
Katrina Drozdov |
2026-10-09 |
3,162 |
2
|
|
An Evaluation of Inception's Mercury Decide
|
Connor Frank |
2026-10-08 |
1,007 |
--
|
|
Trust but Verify: Our first Public Sector Summit
|
Glenn Parham |
2026-10-07 |
1,009 |
--
|
|
Two-Thirds of MiMo v2.6's Coding Tasks Leak the Answer. Are Models That Exploit This Misbehaving?
|
Oliver Chen & Anthony Ozerov |
2026-10-07 |
1,461 |
7
|
|
An Independent Evaluation of TypeSafe's Jev
|
Connor Frank |
2026-10-06 |
2,766 |
1
|
|
Two Room-Temperature Antiferromagnetic Semiconductor Candidates
|
Geby Jaff |
2026-10-04 |
1,771 |
495
|
|
Vals Web Search Index: Evaluating Search for Real Work
|
Nikil Ravi |
2026-10-02 |
1,712 |
--
|
|
Has the Bitter Lesson Come for AI Detectors?
|
Daniel Fein |
2026-09-30 |
611 |
--
|
|
A Lean Proof of the Thomson Problem for Seven Electrons
|
Hung Tran |
2026-09-28 |
1,235 |
--
|
|
Evaluating AI Safety in Teen Conversations
|
Andrea Mock & Caroline Figueroa |
2026-09-23 |
2,541 |
--
|
|
A Faster Shortest Path Algorithm
|
Geby Jaff |
2026-09-20 |
1,761 |
39
|
|
AI Cheating is on the Rise
|
Daniel Fein |
2026-09-15 |
524 |
4
|
|
Vals Environmental Impacts Report
|
Olivia Fowler, Omar Almatov & Daniel Fein |
2026-09-03 |
6,105 |
--
|
|
Claude Fable 5.1 Solves the Cyphral Distich
|
Geby Jaff |
2026-08-31 |
1,421 |
2
|
|
Series A: Always a Higher Peak
|
Rayan Krishnan |
2026-08-13 |
524 |
--
|
|
Child AI Safety
|
Andrea Mock & Glenn Parham |
2026-08-12 |
715 |
--
|
|
Vals Public Sector Memo
|
Rayan Krishnan & Glenn Parham |
2026-07-02 |
470 |
--
|
|
Measuring Healthcare AI Where It Actually Works
|
Rayan Krishnan |
2026-02-23 |
559 |
--
|
|
Behind the Scenes of Vibe Code Bench
|
Rayan Krishnan |
2025-11-26 |
3,339 |
--
|