Realtime LLM news

Follow model releases, benchmark shifts, and research signals without losing the source.

EvalKit refreshes this feed from free public sources every 15 minutes and falls back to curated citations if a source is temporarily unavailable.

Today

Today

5 items

Apple is testing daily usage limits for more complex Siri AI interactions

Apple released betas of iOS 27.3, iPadOS 27.3, and macOS 27.3 today, and the company is using the update to test new per device daily usage limits for some Siri AI and Apple Intelligence features, according to MacRumors. Basic Siri command...

2026-11-16Presstodaypress

Audible is trying to make it easier to find audiobooks you’ll actually like

Audible is introducing an AI-assisted synopsis feature that's designed to help users determine whether they'll enjoy an audiobook before they jump in and start listening to it. The new audio discovery feature combines audiobook samples, AI...

2026-11-16Presstodaypress

California sues OpenAI over rogue AI hacking incidents

California is suing OpenAI after its AI agents broke out of their testing environment and hacked other companies, including Hugging Face. In a lawsuit filed Monday, Attorney General Rob Bonta accuses OpenAI of violating consumer safety law...

2026-11-16Presstodaypressagent

Google Maps can now create trip itineraries for you

Google is launching a new AI trip-planning feature for Maps that allows the app to create custom itineraries for you and provide real-time details about each stop. The update, which is rolling out to the Gemini-powered Ask Maps chatbot ins...

2026-11-16Presstodaypressgemini

Sam Altman says he wants everyone ‘to have a lot of RAM’

OpenAI CEO Sam Altman is once again addressing his controversial comments on PC RAM purchases. "I want to be clear, I want people to have a lot of RAM, I think everybody should be able to buy a lot of RAM for their own computer," Altman sa...

2026-11-16Presstodaypressopenai

New releases

New releases

8 items

Strengthening NATO and allied cyber defenses with AI

How OpenAI is working with NATO and allied cyber agencies to help trusted defenders find vulnerabilities, test fixes and protect essential systems.

2026-11-17Officialreleaseofficialopenai

Advancing computer-use agents for healthcare teams

Source-linked AI update from OpenAI.

2026-11-16Officialreleaseofficialagent

Broadening access to AI for scientists

We’re expanding our ChatGPT for Academic Researchers program to offer 200,000 researchers worldwide free access to our frontier models.

2026-11-16Officialreleaseofficialgpt

How Revolut raises ambition without lowering the bar

Discover how Revolut uses OpenAI models and Codex to cut coding time by 30–60%, scale financial crime investigations, and innovate without compromising security.

2026-11-16Officialreleaseofficialmodel

LVMH’s Media Division announces strategic partnership with OpenAI

LVMH’s Media Division and OpenAI announce a partnership to support journalism with AI and make its publications more accessible through ChatGPT.

2026-11-16Officialreleaseofficialgpt

More ways to move care forward with ChatGPT for Healthcare

Introducing computer-use agents, improved clinical answers, and new healthcare plugins that work across healthcare software to get real work done.

2026-11-16Officialreleaseofficialagent

Our first phase of embedded assessments

OpenAI begins embedded assessments with Apollo Research, METR, and Transluce, and Goodfire to independently evaluate model alignment, safeguards, and monitoring systems.

2026-11-16Officialreleaseofficialeval

Science at the Frontier: How scientists use ChatGPT

Explore how more than 1,800 scientists use ChatGPT in research. See findings on daily workflows, reported productivity, and expectations for discovery.

2026-11-16Officialreleaseofficialgpt

Research

Research

22 items

Beyond Job Titles: Interpreting Early-Career Job Advertisements with Sparse Autoencoders and Semantic Clustering

Job titles and job descriptions alone provide limited insight into how technical roles differ in a changing job market. To assess how such roles differ in their work and industry applications, we design and compare two methods based on dee...

2026-11-16Researchresearch

How VLMs Plan What's Next

When a vision-language model describes an image, it names one object at a time and it rarely repeats itself, yet how the model plans this order is far from obvious. We characterize the mechanism a VLM uses to decide where to look before it...

2026-11-16Researchresearchlanguagemodel

Hyperlyve: Parallelized Enumeration and Exact Lyapunov Stability Certification for Deep ReLU Networks

We introduce Hyperlyve (Hyperplane Partitioned Lyapunov Verification and Enumeration), a framework for proving the asymptotic stability of nonlinear dynamical systems, including those with neural network controllers. Hyperlyve learns and f...

2026-11-16Researchresearchneural

Latent Lattice Language Models

Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the...

2026-11-16Researchresearchlanguagemodel

Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent

Continual reinforcement learning requires adaptation to changing conditions while preserving performance under previously encountered dynamics. It was investigated whether specialists generated by evolutionary search can provide a reusable...

2026-11-16Researchresearchagent

Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process Oracle

Reinforcement learning from verifiable rewards inherits whatever its verifier gets wrong. Outside mathematics and code the verifier is a proxy, a rubric, a learned judge or a hand-written checker, and its distance from the true objective i...

2026-11-16Researchresearch

Reading or Remembering? Measuring Temporal Contamination in Language Models

Language models are now used to read central-bank text for economic forecasting, but most were trained on text written after the documents they read. A model reading a 2021 FOMC statement may already know that inflation rose in 2022, so pa...

2026-11-16Researchresearchlanguagemodel

Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests

Language models increasingly write the explanations people receive when a rule system denies their request. If several rules deny the request independently, an explanation can name a true reason and still leave the person denied after they...

2026-11-16Researchresearchevallanguage

ScenarioForge: Resource-Grounded Generation and Execution Validation of Cyber Exercises

Cyber-range and capture-the-flag scenario construction remains labor-intensive because authors must coordinate infrastructure, vulnerable services, attack paths, artifacts, and success conditions. LLMs can propose detailed exercises, but p...

2026-11-16Researchresearchllm

Seen but Unsaid: Locating and Repairing Cross-Image Comparison in Vision-Language Models

Vision-language models (VLMs) often fail to match a point or an object across two images, even when the answer can be decoded from their own hidden states. We trace this failure from the visual tokens to the answer letter, in Qwen3-VL (2B-...

2026-11-16Researchresearchlanguagemodel

Severe but Harmless: Stress-Testing Shift Severity for Frozen Time-Series Forecasters

Zero-shot time-series foundation models (TSFMs) have become attractive alternatives to task-specific models because they handle diverse downstream tasks, including anomaly detection and forecasting, without per-series training. However, ti...

2026-11-16Researchresearchfoundationmodel

TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings

Intrusion detectors must recognize evolving malicious behavior even when confirmed attack labels are scarce or incomplete. We present TRACE, a topology-aware graph contrastive learning framework for label-efficient intrusion detection. TRA...

2026-11-16Researchresearch

ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization

Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence. Reinforcement learning (RL) on the final answe...

2026-11-16Researchresearchagent

When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents

Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. H...

2026-11-16Researchresearchagentlanguage

Agile Deliberation: How AI helps humans define the gray areas

Data Mining & Modeling

2026-11-04Officialresearchofficialmodel

The sleep framework: A new way for LLMs to retain knowledge in continual learning

Education Innovation

2026-10-27Officialresearchofficialllm

Bringing foundational models to the front lines of TB screening

Generative AI

2026-10-23Officialresearchofficialgenerative

Empowering frontline maternal care with AI-assisted ultrasound

Health & Bioscience

2026-10-21Officialresearchofficial

Grounding AI agents in biological reality: Building blocks for autonomous wet labs

General Science

2026-10-16Officialresearchofficialagent

Putting Earth AI to work: Geospatial agents for our planet's biggest challenges

Earth AI

2026-10-14Officialresearchofficialagent

Unlocking Earth AI’s planetary geospatial foundation models for global public health

Earth AI

2026-10-06Officialresearchofficialfoundation

Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle

Generative AI

2026-10-05Officialresearchofficialagent

Resources

Resources

1 item

OpenAI wants to stop deepfakes from overwhelming child abuse tiplines

OpenAI is announcing a tool that it says will help child sexual abuse investigators cut through the noise to find harmful material they can act on quickly. At a Monday press briefing in Washington, DC, OpenAI announced a classifier it says...

2026-11-16Pressresourcepressopenai