arXiv:2604.08525v3 Announce Type: replace Abstract: Large language models (LLMs) are trained to align with user preferences through methods like…
Category: AI
ScreenSearch: Uncertainty-Aware OS Exploration
arXiv:2605.16024v2 Announce Type: replace Abstract: Desktop GUI agents operate under partial observability: visually similar screens can correspond to…
5 Things Vibe Coding Gets Right and 5 Things It Gets Wrong
Is vibe coding the future of programming or a shortcut to bad code? Let’s look at what it gets right and wrong.
Pander Score: A Continuous Measure of Sycophancy as Epistemic Deference
arXiv:2606.07897v2 Announce Type: replace Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.…
Cognition CEO denies report that SpaceX tried to acquire the startup
SpaceX was reportedly in talks to buy AI coding startup Cognition. SpaceX has already acquired Cursor as it races to catch up to rivals like OpenAI and…
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
arXiv:2604.12616v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual…
Planning under Distribution Shifts with Causal POMDPs
arXiv:2602.23545v3 Announce Type: replace Abstract: In the real world, planning is often challenged by distribution shifts. As such, a model of the…
Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models
arXiv:2604.00547v2 Announce Type: replace Abstract: Unified Multimodal Large Models (UMLMs) integrate understanding and generation capabilities within a…
Chronos: The AI Co-Historian
arXiv:2604.03553v3 Announce Type: replace Abstract: AI is increasingly supporting, accelerating, and automating scientific discovery across subjects. Yet,…
Partnering with CodeAI to prepare the first AI generation
OpenAI and CodeAI are partnering to help students build AI literacy, think critically about AI, and develop the skills to use and shape it responsibly.