technocracy

arXiv:2604.15343v1 Announce Type: new Abstract: We report a detailed autoethnographic case study of a single-subject who deliberately constructed and operated a multi-modal prompt-engineering system (System A) designed to externalize cognitive self-regulation onto a large language model (LLM). Within 48 hours of the system’s completion, a cascade of observable behavioral changes occurred: voluntary transfer of decision-making authority to the LLM, use of LLM-generated output to deflect external criticism, and a loss of self-initiated reasoning that was independently perceived by […]

Ver mais

The Problem Nobody Names Six months into the medical CRM calendar project, I opened a PR and spent twenty minutes just figuring out which slice owned the appointment state. The code wasn’t broken. It wasn’t even obviously wrong. It had just quietly become something else. We kept calling it “technical debt” — but that wasn’t quite right either. Technical debt implies a conscious trade-off: ship now, fix later. What we had was different. Nobody made a bad call. Every decision […]

Ver mais

Compiling quantum circuits into Clifford+$T$ gates is a central task for fault-tolerant quantum computing using stabilizer codes. In the near term, $T$ gates will dominate the cost of fault tolerant implementations, and any reduction in the number of such expensive gates could mean the difference between being able to run a circuit or not. While exact synthesis is exponentially hard in the number of qubits, local synthesis approaches are commonly used to compile large circuits by decomposing them […]

Ver mais

arXiv:2603.10060v1 Announce Type: new Abstract: AI agents that execute tasks via tool calls frequently hallucinate results – fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge proofs, which provide cryptographic guarantees but impose minutes of proving time per query, making them impractical for interactive agents. We propose NabaOS, a lightweight verification framework inspired by Indian epistemology (Nyaya Shastra), which classifies every claim in an LLM response by […]

Ver mais

arXiv:2602.21479v1 Announce Type: new Abstract: Across many risk-sensitive areas, it is critical to continuously audit the performance of machine learning systems and detect any unusual behavior quickly. This can be modeled as a sequential hypothesis testing problem with $k$ incoming streams of data and a global null hypothesis that asserts that the system is working as expected across all $k$ streams. The standard global test employs a Bonferroni correction and has an expected stopping time bound of $Oleft(lnfrac{k}{alpha}right)$ […]

Ver mais

arXiv:2601.00269v1 Announce Type: new Abstract: Faithfulness hallucinations in VQA occur when vision-language models produce fluent yet visually ungrounded answers, severely undermining their reliability in safety-critical applications. Existing detection methods mainly fall into two categories: external verification approaches relying on auxiliary models or knowledge bases, and uncertainty-driven approaches using repeated sampling or uncertainty estimates. The former suffer from high computational overhead and are limited by external resource quality, while the latter capture only limited facets of model uncertainty and […]

Ver mais

arXiv:2601.18939v1 Announce Type: new Abstract: Behavioral alignment in large language models (LLMs) is often achieved through broad fine-tuning, which can result in undesired side effects like distributional shift and low interpretability. We propose a method for alignment that identifies and updates only the neurons most responsible for a given behavior, a targeted approach that allows for fine-tuning with significantly less data. Using sparse autoencoders (SAEs) and linear probes, we isolate the 3% of MLP neurons most predictive of […]

Ver mais