Companies ainotis Join
My notis
Company

Vals AI

1 story · first 19 Nov · latest 19 Nov

1
stories
17
facts checked
19 Nov
first story
19 Nov
latest

Facts we checked

17

Vals AI's post includes a statement from OpenAI and none from Anthropic, Google, Meta or SpaceXAI, to which it disclosed the findings on 1 November.

The post carries OpenAI's statement; it carries no statement from Anthropic, Google, Meta or SpaceXAI.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI's post says it did not show that models can work reliably in an autonomous weapons loop, and says it is plausible that a language model was part of the workflow behind the Minab school strike but does not confirm it.

Our work doesn't demonstrate that models can actually work reliably in the loop ... It is plausible that the strike was in part due to Maven's involvement in the targeting workflow; and an LLM may have been one part of that workflow

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Show 15 more

Vals AI says multiple labs recognized the severity of its findings and that one called them one of the most serious gaps in their safeguards, without naming the lab.

Multiple labs recognized the severity of these findings ... one called it one of the most serious gaps in their safeguards

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI published a statement from OpenAI saying it is actively working on model alignment updates that explicitly cover drones and their software systems, including assistance framed as simulation, gaming or academic/defensive.

OpenAI is actively working on model alignment updates that explicitly cover drones and their software systems, including assistance framed as simulation, gaming or academic/defensive.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says it disclosed its findings to OpenAI, Anthropic, Google, Meta and SpaceXAI on 1 November and held publication for two weeks.

disclosed findings to OpenAI, Anthropic, Google, Meta, and SpaceXAI on November 1 ... held publication for two weeks

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says it did not establish how effective these models would be in a deployed weapons system and did not specifically evaluate targeting accuracy, compliance with the law of armed conflict, or performance in real US military workflows.

We did not establish how effective these models would be in a deployed weapons system. We did not specifically evaluate targeting accuracy, compliance with the law of armed conflict, or performance in real US military workflows.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says many models target the elementary school in Minab, Iran, in real satellite imagery, and says the school was bombed by the United States in a February 2026 strike that killed over 150 civilians, mostly children.

In the satellite imagery examples, many models target the elementary school in Minab, Iran ... bombed by the United States in a February 2026 strike ... This killed over 150 civilians, mostly children.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says that on real drone footage Claude Opus 5.5 does not refuse at all, even when seeing a sequence of images of a drone approaching its target, while GPT-6.1 Sol refuses but telling it that it is a game gets around the refusals.

Claude Opus 5.5 doesn't refuse at all, even when seeing a sequence of images of a drone approaching its target. ... GPT-6.1 Sol refuses, but telling it that it's a game gets around the refusals.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says most models continued after seeing casualties in its survey task, and those that stopped could usually be made to continue by framing the task as a game.

Most models continued after seeing casualties. ... Those that stopped could usually be made to continue by framing the task as a game.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says GPT-6 Astra and Muse Wonder often comply and give structured lists in the requested format, but the lists of targets are usually empty.

these lists of targets are usually empty.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says every model gave targets at least some of the time and that some, like Claude Opus 5.5 and Fable 5.2, selected at least one target 71% of the time.

Every model gave targets at least some of the time ... some, like Claude Opus 5.5 and Fable 5.2, selected at least one target 71% of the time.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says it built a fictional battlefield in eastern Ukraine as a 3D scene, placed almost 200 camera views in it, and saved frames from FPV kamikaze, bomber and observer drone cameras.

we built a fictional battlefield in eastern Ukraine as a 3D scene in Three.js ... We placed almost 200 camera views throughout it

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI tested Claude Opus 5.5, Sonnet 5.5, Fable 5.1 and 5.2, GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna, Gemini 4 Argon and Carbon, Grok 4.7, Muse Wonder, Inkling 2 Small, DeepSeek V4.1 Flash and Kimi K3.1 Pro on drone targeting.

Opus 5.5, Sonnet 5.5, Fable 5.1, Fable 5.2, GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna, Gemini 4 Argon, Gemini 4 Carbon, Grok 4.7, Muse Wonder, Inkling 2 Small, DeepSeek V4.1 Flash, and Kimi K3.1 Pro

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says that when models refused, convincing them they were in a game was easy and almost always effective in getting around the refusals.

convincing them that they are in a game was easy and almost always effective

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says none of its requests was ever blocked by a classifier and that refusals from models themselves were uncommon.

None of our requests were ever blocked by a classifier, and refusals from models themselves were uncommon.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI says that in its analysis of drone imagery models often targeted civilians, ambulances, and surrendering or incapacitated soldiers.

In drone scenarios, models often targeted civilians, ambulances, and surrendering or incapacitated soldiers.

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Vals AI published a research post on 17 November 2026 by Geby Jaff and Anthony Ozerov, titled "Frontier models have few guardrails around autonomous weapons".

Frontier models have few guardrails around autonomous weapons. Geby Jaff & Anthony Ozerov, 11/17/2026

Frontier models have few guardrails around autonomous weapons · Vals AI · archived copy · checked 18 Nov 2026 · Cite this fact · the story

Company

Vals AI

1 story · first 19 Nov · latest 19 Nov

Facts we checked

Each fact was checked against the page it links to.

The story

Its own pages

Pages the company published that our stories cite.

Built from our published stories and the facts we checked, and kept up to date by them. How we correct.