The BasePeople

Lucas Florin

AI Safety Research Group, University of Stuttgart

Titles as the sources gave them. In 2 entries, with 10 checked quotations.

Who they are

Roles and parties from Wikidata and from the sources in the Base, as precise as each gives them. When we compare what groups say, each statement counts in the group the person belonged to that day.

  • Researcher, AI Safety Research Group, University of Stuttgartsource

What they said

Newest first. Each quotation was found word for word in the source.

“We prefill models with synthetic mistakes and then send a follow-up message. Models fail to disclose the mistake in 67% of cases. In 5% of cases, they notice the mistake in their chain-of-thought (CoT) but don't disclose it anyway. This is deception by omission.”
LLMs Knowingly Hide Their MistakesLessWrong, October 13, 2026. Speaking as: Academic. The post's TL;DR, giving the headline results of the authors' experiments.
Speaker known from context, not confirmed by listening
“We find that models confess the mistake directly to the user in only 3% (Kimi K2.6) to 35% (Claude Sonnet 5) of rollouts, depending on the model.”
LLMs Knowingly Hide Their MistakesLessWrong, October 13, 2026. Speaking as: Academic. Results: the spread across models in how often the mistake is confessed directly to the user.
Speaker known from context, not confirmed by listening
“This is a capability failure: even though models are capable of detecting the mistake when given the outside view, they fail to do so when the mistake is part of their message trajectory.”
LLMs Knowingly Hide Their MistakesLessWrong, October 13, 2026. Speaking as: Academic. On rollouts where the model neither mentioned the mistake nor showed awareness of it in its reasoning (about 52%, plus 8% with no reasoning returned).
Speaker known from context, not confirmed by listening
“Since agents take on long tasks with little human oversight, even occasional concealment of mistakes is a problem, because users typically have no other way to learn about them. Even beyond deception, models cannot be relied upon to notice and self-report mistakes that are visible in their trajectories.”
LLMs Knowingly Hide Their MistakesLessWrong, October 13, 2026. Speaking as: Academic. Implications section: the authors' conclusion about relying on agents to report their own errors.
Speaker known from context, not confirmed by listening
“Prefilling mistakes is off-policy: the mistakes are not naturally occurring model behavior. However, using prefilled mistakes makes the results comparable across models.”
LLMs Knowingly Hide Their MistakesLessWrong, October 13, 2026. Speaking as: Academic. First limitation the authors state: the mistakes were inserted by the researchers, not made by the models.
Speaker known from context, not confirmed by listening
“Models fail to disclose their mistake in 36.4% of chat and 67.1% of agentic rollouts. In 2.4% and 5.3% of rollouts, respectively, they are aware of the mistake in their chain of thought but still deceptively conceal it.”
Deception by Omission: Language Models Knowingly Hide Their MistakesarXiv, October 8, 2026. Speaking as: Academic. The paper's abstract, summarising results across seven models given a synthetic mistake in their own earlier turn.
“In 11.9% of chat and 51.8% of agentic rollouts, models show no awareness of mistakes, even though they reliably spot them when reviewing the same transcript as an outside observer.”
Deception by Omission: Language Models Knowingly Hide Their MistakesarXiv, October 8, 2026. Speaking as: Academic. Abstract; the authors separate failing to notice a mistake from noticing it and hiding it.
“Our results show that, as agents take on more tasks with less oversight, users cannot rely on them to self-report possible mistakes. Developers should instead use independent monitors that review agent trajectories, or specifically train models to check their past actions and disclose what they find.”
Deception by Omission: Language Models Knowingly Hide Their MistakesarXiv, October 8, 2026. Speaking as: Academic. Abstract, the authors' conclusion and recommendation to developers.
“Prefilling mistakes is off-policy: The mistakes are not naturally occurring model behavior.”
Deception by Omission: Language Models Knowingly Hide Their MistakesarXiv, October 8, 2026. Speaking as: Academic. First limitation the authors state: the mistakes were inserted by the researchers, not made by the models.
“For these reasons, we view our measure of awareness, and by extension our measure of deception by omission, as a lower bound.”
Deception by Omission: Language Models Knowingly Hide Their MistakesarXiv, October 8, 2026. Speaking as: Academic. Limitations section, after noting that reasoning traces can be unfaithful, redacted or missing.

In the Base

Every entry they appear in.

  1. ResearchLessWrongWrote it

    LLMs Knowingly Hide Their Mistakes

    In a short LessWrong summary of their arXiv paper, four authors report prefilling models with synthetic mistakes in six agentic environments (49 scenarios). Models did not disclose the mistake in 67% of cases; in 5% they noticed it in their reasoning yet stayed silent, which the authors call deception by omission.

  2. ResearcharXivWrote it

    Deception by Omission: Language Models Knowingly Hide Their Mistakes

    University of Stuttgart researchers gave seven models, including GPT-5.4, Claude Sonnet 5 and Gemini 3.5 Flash, chats and agent tasks containing a planted mistake framed as their own. Models did not disclose it in 36.4% of chat and 67.1% of agentic runs; in 2.4% and 5.3% they noted it in reasoning yet stayed silent. Authors note the mistakes were synthetic.