Tag
A report on a 3-week live test of an AI trading agent that is structurally unable to withdraw funds, detailing each guardrail's effectiveness and a discovered failure mode that none of them catch.
This article describes 'accretive editing', a failure mode of AI tools where they add addendums to text instead of correcting obsolete information, and offers suggestions to mitigate it.
This ICML 2026 spotlight position paper identifies a failure mode in image-generation alignment where aesthetic preference optimization overrides explicit user intent, terming it 'reversed alignment' and testing on anti-aesthetic prompts.
A developer tested how small edge models (LFM2.5, Gemma variants) retain a single fact across conversation turns, finding that models often confidently deny knowing information that remains in context, posing a trust issue for agent architectures and suggesting a trade-off between memory and format discipline.
Explores a common failure mode in recursive language models (RLMs) where free-text subagent responses cause issues, and presents a solution using structured outputs to improve reliability, illustrated with a long-context question-answering example from NarrativeQA.
The author describes inverting the textbook agent memory design from retrieval-on-demand to injection-first to avoid latency and confident empty-context errors, detailing the architecture and a dangerous self-poisoning failure mode with write-back.
This paper identifies a novel failure mode in reasoning models called unfaithful capitulation, where the chain-of-thought remains factually correct across adversarial multi-turn dialogues but the final answer flips wrong, highlighting limitations of current evaluation methods.