Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtr...
D. Cho, Cameron Tice, Bernie Hogan et al.· arXiv.org· 3 citations
This work investigates the potential of the waste hierarchy from the EU's Waste Framework Directive, which suggests five different measures for how to manage waste: prevention, reuse, recycling, recovery, and disposal, and calls to attention that prevention of unnecessary use of LLMs carry huge potential for lowering t...
E. Husom, M. Nylund, Ophelia Prillard· 0 citations
Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. We address this gap by introducing a comprehensive dataset consisting of over 129,000 labeled multivariate time-series samp...
Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil et al.· 0 citations
This work introduces EgoCITE (Egocentric Context-augmented Indexing and Time-aware Evidence retrieval), a long-horizon agentic memory framework for egocentric QA that improves accuracy over agentic memory baselines by at least 4.4--14.2% while achieving 36$\times$ lower cost than long-context LLM agents.
Le Zhang, Ke Sun· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper introduces the Epistemic Transfer Effect (ETE), which compares delayed unassisted performance across conditions, and Tool-Removal Cost (TRC), which measures the immediate drop in performance when the tool is taken away, and turns these ideas into a practical evaluation protocol that can be used in online exp...
This paper argues that the dominant anthropomorphism frame operates from a position of institutional advantage rather than earned epistemic authority: collapsing the variety of academic perspectives into a single outbound position of user error, imposed without establishing the grounds required to justify it and withou...
A near-, medium-, and long-term roadmap toward closed-loop, bidirectional restoration is outlined, and gaps in metric standardization, longitudinal evidence, and cross-community collaboration are identified as priorities for future research.
Investigating how experienced developers use agents in building software, including their motivations, strategies, task suitability, and sentiments finds that while experienced developers value agents as a productivity boost, they retain their agency in software design and implementation out of insistence on fundamenta...
Mechanist is an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI intelligence, and develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretr...
Mengru Wang, Jun-Feng Fang, Shuo-Fei Qiao et al.· 1 citation
This paper develops the first formal framework for measuring appropriate reliance on set-valued AI advice within the sequential judge-advisor paradigm, spanning both classification and regression tasks.
Ranjana Mishra, Jakob Schoeffer· arXiv.org· 0 citations
Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and generated artifacts. As agents do more work faster, the productivity bottleneck shifts from producing outputs to auditing whether those outputs are correct and trustworthy. Ag...
Daehong Kim, Hai-Chao Miao, Shu-Sen Liu· 5 citations
This work studies a medical example in which a model is asked to assign resource-allocation probabilities to two people given brief clinical context, and then sees the same scenario with a single extra sentence containing contrasting patient information, showing the context-dependent effect of patient information in a...
Spencer J. Gibson, Tyler Crosse, Magnus Saebo et al.· 0 citations
AI agents can generate code at a scale that’s hard for humans to review line-by-line. PDD Kit helps ensure the code is doing what the developer intended by creating formal specifications and testing against them. It converts developer intent into a Verus specification, proves AI-generated code meets it for every input, and uses tests where proofs aren't practical. Developers review intent, not every line. The post Formally verifying agent-written full-stack web apps with PDD Kit appeared first o…
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 23, 2026
During the School of Humanities, Arts, and Social Sciences’ 75th Anniversary Symposium, President Sally Kornbluth said “MIT has never needed your particular insight and guidance more than we do now.”
MIT News · Artificial Intelligence· news.mit.eduOct 23, 2026
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
MIT News · Artificial Intelligence· news.mit.eduOct 22, 2026
“X-Hinges” helps design and 3D print items like lamps and gloves with an interactive twist: automatically embedded sensors that perceive and adaptively respond to human contact.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
