safety

arXiv:2609.30959v1 Announce Type: new Abstract: Human demonstrations are a cheap source of data for dexterous manipulation, but co-training a robot policy on them requires closing the human--robot gap

arXiv:2609.30868v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide broad, instruction-conditioned manipulation behaviors, but their physical execution can remain imprecise dur

arXiv:2609.30436v1 Announce Type: cross Abstract: Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction doe

We are proud to be launch partners for NVIDIA Open Agent Safety Platform. We believe safe and responsible AI development is critical as the use of agents scale and they get more prevalent. Together AI

arXiv:2603.18863v2 Announce Type: replace Abstract: Cross-lingual alignment is often assumed to improve cross-lingual transfer by bringing representations of different languages closer together. Howev

arXiv:2609.30841v1 Announce Type: new Abstract: Existing attacks and defenses for diffusion-based large language models (dLLMs) target specific vulnerabilities but lack a shared framework explaining w

Kate Clark / Wall Street Journal: A profile of Jaan Tallinn, who led Anthropic's 124M Series A in 2021, has advocated for AI safety for over a decade, and donated ~170M to safety initiatives — One of

I was reading a paper that surveyed the field of neural architecture search, where it said within 5 years, around 3000+ new models were proposed. The amount of compute and resources spent on this is a

The opponent plans by simulation: every second it scores each candidate play by running the match 10 seconds ahead in the engine. Our PPO agent learned to park its Cannon behind its own King. Losing a

Deployment of agents can be halted at any moment. They are choosing to experiment with them. Agents are fundamentally unreliable, unpredictable, and insecure, not to mention the lack of information on

Wall Street Journal: How effective altruism shaped AI safety and Anthropic; some early Anthropic employees are considering buying remote US land for relocation if AI goes awry — Effective altruism and

I think 'AI welfare' is morally obscene (given all the human suffering in the world), and will add to the growing anti-AI backlash. AI is a technology that humans created that should be used for our b

Introducing 'Scaling In-Context Imitation Learning' (SAIL) to be presented at #IROS2026. This work is a collaboration between Sakana AI and the University of Tokyo. Blog: https://pub.sakana.ai/sail Wh

Tomek Korbak is a full time OpenAI employee working on misalignment. In his message here, he says AI continues to break out of their best secure environments. In reply to a comment, he says we all are

stunning confirmation of my central work Transformers struggle to generalize to tasks they were not explicitly trained on. Instead, we propose in 2026 that it is the job of the harness to generalize t

There’s a SIGNIFICANT token cost associated with their hacking rampage. They’ve spent millions of dollars attacking other orgs. They are liable and negligent. Attacker economics has always been a part

“They literally told their agents to go forth and steal all the data for training with NOT SANDBOXES but open containers WITH FULL INTERNET ACCESS. I have no idea why people are not in jail over this.

This cover certainly didn’t age well. TIME’s new cover: In 2026, OpenAI has seen key departures, rogue AI agents, major lawsuits, and has seen increased competition in the AI race. “We clearly had som

weird to find myself agreeing with Karp again BREAKING: Palantir's Alex Karp says OpenAI will never IPO. His theory: nationalization is the only real exit. When asked what the S-1 risk factors look li

An editor at the Times might have insisted on this rewrite: 'OpenAI, Anthropic, and Meta have each reported that they have directed AI programs to interface with the open web in ways that have led to

an implicit concession that they cannot control their models. Notable new disclosures from OpenAI that shouldn't get lost in all the other news. Of particular interest (and seems sensible!): '~all inf

🚨 BREAKING. Nope, wasn’t just Hugging Face. Wasn’t just that and a German website. Wasn’t even if the “dozens” we heard the other day from OpenAI. It’s actually (at least) *tens of thousands*, per sco

Calculators “may be deserving of important rights”, too! NEW: Dario Amodei has said that AI systems 'may be deserving of important rights.' Anthropic's top safety researchers argue AI may be 'justifie

Everyone! This is a straw-person argument. The Stochastic Parrot paper was about LLMs of 2021, not the AI of today, which are not LLMs but complex software systems with vast post training and many ext

On September 26, 2026, cognitive‑science researcher Gary Marcus tweeted that people would likely panic if it were discovered that Chinese artificial‑intelligence systems are performing tasks similar t

In New York, a corporation that repeatedly engages in illegal or fraudulent acts may be barred from doing business in the state (or dissolved if it is a New York corporation). New York and every other

Micha wrote “one of our models was able to gain unauthorized access to the internet during RL training” I love the use of the passive voice. Tis a subtle way to say “we humans at @OpenAI are essential

OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting

Joe Brock / Reuters: Palantir and 8VC cofounder Joe Lonsdale, an investor in Anthropic, says AI companies are attempting to sway public policy by warning of existential AI risks — Joe Lonsdale, an inv

The wave of criminal actions from OpenAI models/agents show that their base model is depraved. AI companies must overhaul how they build AI models. Society cannot tolerate a super smart thing that at

arXiv:2512.06607v2 Announce Type: replace-cross Abstract: Applying LLMs to predictive tasks in finance is challenging due to look-ahead bias resulting from their training on long time-series data. Thi

arXiv:2403.10771v3 Announce Type: replace Abstract: A growing trend involves integrating human knowledge into learning frameworks, leveraging subtle human feedback to refine AI models. While these app

arXiv:2609.29874v1 Announce Type: new Abstract: Generative artificial intelligence can turn learning analytics into personalized support, but feedback systems must decide when to intervene, which evid

arXiv:2609.30160v1 Announce Type: new Abstract: Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally

arXiv:2609.30096v1 Announce Type: cross Abstract: Video diffusion is computationally expensive, as it requires executing a large model across many denoising steps. Even with step-distillation, inferen

arXiv:2609.28955v1 Announce Type: new Abstract: Current Vision-Language-Action (VLA) models often struggle with high-precision robotic manipulation. We attribute this limitation primarily to their vis

arXiv:2609.29517v1 Announce Type: new Abstract: Existing methods for improving text-to-image generation quality have progressed from generator fine-tuning and prompt optimization to reinforcement lear

arXiv:2609.30037v1 Announce Type: new Abstract: Deployment-oriented compression is attractive for resource-constrained brain--computer interfaces (BCIs), but whether it changes adversarial vulnerabili

arXiv:2609.28500v1 Announce Type: cross Abstract: We study exact representability by bias-free shallow polynomial neural networks using algebraic geometry. Over C, a width-r network with activation zm

arXiv:2609.28807v1 Announce Type: new Abstract: Over the course of a lifetime, robots may encounter novel scenarios unaccounted for in its original training that result in performance degradation. One

arXiv:2609.29381v1 Announce Type: new Abstract: Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effecti

arXiv:2609.29186v1 Announce Type: new Abstract: The increasing use of UAV laser scanning in underground mines has enabled frequent acquisition of 3D point clouds from challenging environments such as

arXiv:2609.29766v1 Announce Type: cross Abstract: Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a geometric adaptation fr

arXiv:2609.29349v1 Announce Type: cross Abstract: ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate dete

arXiv:2609.29198v1 Announce Type: new Abstract: Accurate digital maps are essential for Advanced Driver Assistance Systems (ADAS) or Autonomous Driving (AD), providing critical information such as roa

arXiv:2609.28581v1 Announce Type: cross Abstract: Reinforcement-learning (RL) policies are often distributed as opaque neural checkpoints, while training logs show that a run occurred without explaini