probes

This paper identifies 'perfect aliasing' in truth probes for AI models, where probes fitted on compliant contexts fail to distinguish truth from prescribed actions, and shows that mixed-context training improves detection.

This paper investigates the relationship between spontaneous and instructed deception in large language models, specifically Llama-3.1-70B-Instruct, finding asymmetries in detection and causation between the two settings.

This article explains how Kubernetes probes, including startup, readiness, and liveness probes, work to improve application resilience, with interactive demos demonstrating their functionality.

GoodfireAI shares research on using probes to improve LLM calibration and detect reasoning faithfulness, and a hackathon using their product Silico for targeted fine-tuning with parameter decomposition.

The author asks how to analyze the relative 'strength' of probes in neural networks, discussing challenges such as limited vocabulary size and model capacity, and using an example from Google Gemini to illustrate failure cases.

This research presents probe-targeted fine-tuning (LoRA) to make LLMs verbally express their internal confidence, achieving causal control over confidence outputs and demonstrating that models often know when they are right or wrong but fail to articulate it.