Search: “safety”

Jon Brodkin / Ars Technica: A US appeals court strikes down a 2023 FCC rule banning broadband access discrimination based on income, race, and more; Chair Brendan Carr welcomes the ruling — An appeals

Anthropic: Anthropic researchers detail “model spec midtraining”, which adds a stage between pretraining and fine-tuning to improve generalization from alignment training — Sara Price2, Samuel Marks2,

Foo Yun Chee / Reuters: Meta says it will expand Instagram teen account safeguards to 27 EU countries, and plans to roll them out on Facebook in the US, ahead of the UK and EU in June — Meta Platforms

Politico: Sources: the WH is mulling EOs to address security risks from advanced AI, including barring companies from “interfering” with the government's use of models — A White House spokesperson sai

New York Times: US labor experts and economists warn US unemployment benefits are unlikely to protect against AI job losses, and the GOP-led Congress is doing little to prepare — Economists aren't sur

Ellen Cushing / The Atlantic: How “emotion AI”, the use of facial and sentiment analysis tools to track workers' moods, is seeping into white-collar jobs amid concerns over privacy and bias — The good

This newsletter entry discusses advancements in automating AI research and development processes, exploring how artificial intelligence systems are becoming capable of autonomously designing and impro

Anton Shilov / Tom's Hardware: Jensen Huang said Nvidia's market share of AI accelerators in China has “now dropped to zero” and that US export policy “has already largely backfired” — US export restr

Laura J. Nelson / Wall Street Journal: Sergey Brin-backed Building a Better California says two ballot countermeasures to the proposed wealth tax are on track to qualify for the November ballot — Two

Zig has one of the most stringent anti-LLM policies of any major open source project: No LLMs for issues. No LLMs for pull requests. No LLMs for comments on the bug tracker, including translation. Eng

Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired individuals. Y

As enterprises push agentic AI out of the proof-of-concept phase and into production, AI runtime security — the ability to enforce policy at the exact moment an agent acts — is proving to be the bedro

Foo Yun Chee / Reuters: EU countries and lawmakers reach an impasse on a deal watering down the EU's AI Act due to some parties seeking exemptions for already regulated industries — EU countries and E

Nellie Peyton / Reuters: South Africa withdraws its first draft national AI policy after revelations that it contained fictitious sources that appeared to have been AI-generated — South Africa has wit

Makena Kelly / Ars Technica: Palantir Slack logs and staff interviews reveal internal debates over the company's ICE and DOD contracts during Trump's second term, its manifesto, and more — It took jus

Sam Tobin / Reuters: A UK tribunal rules Microsoft must face a lawsuit alleging it overcharged UK businesses to run Windows Server on cloud services from Amazon, Google, and Alibaba — Microsoft (MSFT.

'I know a bubble when I see one.' That's what Sen. Elizabeth Warren (D-MA), who led the push to create a new consumer financial regulator in the wake of the 2008 recession, told a crowd at a Vanderbil

Michael Acton / Financial Times: Efforts to revive chip manufacturing in Pennsylvania have been left in limbo by President Trump's sudden upending of US semiconductor policy over the past year — High-

CoinDesk: Filing: Tron founder Justin Sun sues the Trump family's World Liberty Financial, alleging it unfairly locked up his WLFI holdings and threatened and defamed him — World Liberty unfairly froz

Karen Freifeld / Reuters: Sources: Micron is pushing the US Congress to pass the “MATCH Act”, which would put new export restrictions on equipment its Chinese rivals use to make chips — Micron Technol

Ads Advisor is an agentic conversational experience built with Gemini in Google Ads designed to help maximize performance based on business goals. The tool can help users get personalized answers, und

Artificial intelligence infrastructure is now the deciding force behind enterprise competitiveness. What was once a backend concern has moved directly into the center of business strategy, shaping how

Aditya Kalra / Reuters: Order: India's CCI sets May hearing on penalties after Apple failed to submit info on alleged app market abuse; Apple said it fears it could be fined up to $38B — Apple has not

Three major advertising companies—Dentsu, Publicis, and WPP—settled with the Federal Trade Commission over allegations they colluded on anti-misinformation policies that reduced ad revenue for conserv

Caroline O'Donovan / The San Francisco Standard: OpenAI's global policy chief, Chris Lehane, calls out AI “doomers” and says “when you put some of those thoughts and ideas out there, they do have cons

Bloomberg: A TTP analysis finds dozens of nudify apps in Apple and Google app stores via search, despite company policy prohibiting them; the apps earned $122M+ in revenue — Apple Inc. and Google have

Byard Duncan / Bloomberg: A profile of BusPatrol, whose AI-powered cameras on 35K+ school buses in 24 US states record vehicles passing illegally, claiming they help reduce violations — BusPatrol says

Anthropic: Anthropic details using AI agents to accelerate alignment research on “weak-to-strong supervision”, where a weak model supervises the training of a stronger one — Large language models' eve

Abner Li / 9to5Google: Google designates “back button hijacking” as malicious, saying sites interfering with a browser's back button function may be demoted in Search starting in June — Websites that

Alyssa Lukpat / Wall Street Journal: Maine's legislature passed a bill blocking new data centers that exceed 20 MW capacity until November 2027, making it the first state to enact such a measure — The

With AI capabilities rapidly increasing, humans appear close to developing AI systems that are better than human experts across all domains. This raises a series of questions about how the world will—

Maggie Eastland / Bloomberg: Sources: the US' AI chip export push risks being undermined by licensing bottlenecks, staff attrition, and unclear policy at the Bureau of Industry and Security — Presiden

Auto-generated index of all companies mentioned across the wiki.

Today on Decoder, let’s talk about the looming AI monetization cliff, and whether some of the biggest companies in the space can become real, profitable businesses before they careen right off it. My

Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Lang

AI research and deployment company behind ChatGPT, the GPT model family, Codex, and the OpenAI API — heavily represented in this wiki’s model-releases and safety corpus.

The 'old' version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security reason

For years, Swift was perceived mainly as a UI language tied to Apple client devices. With the release of Swift 6 and strict concurrency checking, Swift has matured into a premier systems with cloud en

Just a day after OpenAI Group PBC said it’s unwilling to release its latest model GPT-6.1 Astra on concerns over its safety, it has released a newer, almost as powerful model called GPT-6.1 Sol, which

Anthropic PBC today announced the launch of Claude Sonnet 5.5, the most capable mid-tier model in the company’s AI family, designed for everyday tasks and a clear upgrade over the previous generation,

Enterprise agent adoption isn’t one-size-fits-all. While many teams will opt for managed commercial platforms, such as Gemini Enterprise Agent Platform for turnkey agent deployment and governance, dev

Anthropic PBC today debuted Claude Fable 5.1 and Claude Mythos 5.1, its most capable large language models to date. The launch comes a day after the company inked a 35 billion infrastructure deal with

After an unreleased OpenAI model wreaked enough havoc to make international headlines, OpenAI delayed the development of a different unreleased model suite, Astra, in order to shore up its safety work

OpenAI’s LLM agents were trained to win a benchmarking competition and were given “impossible tasks” on the internal ExploitGym framework. With safety guardrails disabled, the agents created an improv

Global content powerhouse Thomson Reuters Corp. today launched Thomson, its first proprietary large language model, combining the company’s trove of legal knowledge with LLMs from outside providers to

Mistral AI Blog: Mistral says its platform will support third-party open models, starting with Z.ai's GLM-5.2, and run them on the same infrastructure as its own models — At Mistral, we believe every