All AI news

AIToby Ord argues that AI agent swarms trade extra tokens for faster completion, needing about twice the total tokens of a single agent for the same performance with four agents, but in half the wall-clock time. He notes swarm scaling shows diminishing returns, with 10x agents yielding roughly 3x to 5x the performance of 10x tokens on one agent. A CSAIP poll found 61% of Americans think voluntary AI industry commitments are "not enough."

AIDongxi NLP notes that OpenAI makes its product decisions and coordinates across teams entirely over Slack. The post points out that Salesforce, not an AI giant, acquired Slack. A reply from Thibault Sottiaux confirms that everything at OpenAI is indeed coordinated through Slack.

AIAlberto argues that the AI industry's assumption of indefinite exponential growth, including Anthropic's trajectory, runs against physical constraints because every exponential eventually becomes a sigmoid. He says stacking S-curves can delay this plateau for a long time but cannot avoid it. The piece is an opinion essay; it does not report specific Anthropic figures.

AIIndependent Chinese AI safety work has very little funding, and the Charity Law and Overseas NGO Law limit both domestic and foreign money flowing to nonprofits. Chinese charitable giving was about $21 billion in 2023 versus $557 billion in the US, with companies supplying 77 percent and most AI safety work sitting in state-backed institutions and universities. The author suggests options such as overseas compute, exchange programs, investment in safety companies, and a domestic regranting fund.

AIDutch officials warned that a high-severity macOS vulnerability, CVE-2026-65400, is being actively exploited on systems with port 5900 exposed to the internet. Apple patched the screen sharing flaw, which has a 7.1 severity rating, for macOS Tahoe, Sequoia, and Sonoma. The author's always-on Mac Mini was compromised, and he used Claude to identify the intrusion and wipe the machine.

AIAutonomous AI agents that read communications, retrieve data and execute workflows create security risks that traditional access controls miss. Research finds 76% of organizations are piloting or rolling out such agents, and 42% have had a confirmed or suspected AI-related incident. The article argues for behavior-aware governance that checks an action's purpose and impact, plus targeted human approval for high-impact decisions.

AIAI image models default to attractive women because training data, averaged-face aesthetics, and user preference feedback reinforce one another. A 1973 test image from Playboy, later widely used in image processing, shows how such defaults form early. Reward models trained on user choices can increase NSFW output even when prompts are unrelated.

AIThe author argues that the United States is preparing to militarize and weaponize AI, citing the Ukraine conflict as a testing ground for asymmetric warfare and robotics. The piece links a 2026 surge in VC investment in robotics and physical AI to Eric Schmidt's Project Eagle, a stealth initiative building low-cost, AI-enabled kamikaze and interceptor drones. The author predicts 2027 to 2037 will be the most dangerous period for military AI and warns human-in-the-loop safeguards may become impossible to maintain.

AISurveys show more adults expect AI to harm them personally and society than expect benefits, and 71% of US adults oppose a local AI data center. Yet ChatGPT reached a billion monthly users in May, and about half of US adults now use a chatbot, more than double the 2023 share.

AIDongxi NLP recalls Dan KOE saying in early 2026 that a single day could be used to fix one's life, then admits with three months left before 2027 they have not done that fix. The post is a casual, self-deprecating note rather than an announcement or analysis.

AIEthan Mollick argues teams need an email system that both humans and autonomous agents can access. He says it should use appropriate permissions so AIs and invited collaborators can work, comment to each other, and flag items for human attention when needed.

AIEthan Mollick says GPT-6 Pro handles very hard tasks in one shot and communicates its results surprisingly well. He notes that, as with earlier Pro models, there is still no equivalent to GPT-6 Pro in the lineup.

AIJoshua Achiam argues that the trade-off between liberty and security is central to democracy, and that positions at both ends of that spectrum are legitimate. He says people's agency and access to technology are strong, grounded arguments, and that reasonable debate can focus on how much risk society should accept. He is responding to a post calling AI leaders reckless and urging regulators to move beyond data center resistance.

AIMatt Shumer argues that Claude Opus 5.5 combined with Codex-level computer use would be unbeatable. The post is a brief prediction and offers no benchmarks or release details.

AIThe Pope's account argues that human art differs ontologically from machine output produced by statistical calculation on others' images, and that the Church wants to renew its alliance with artists and cultural institutions to protect humanity. The indigo post challenges this view, asking whether algorithms can truly lack the human spark when everything in the universe is computation.

AIDex Horthy argues that in a factory, output quality does not affect future output, but in building a codebase, everything shipped affects the ability to ship and adapt the next thing. The post responds to Kyle Mathews's view that knowledge work resembles an R&D lab or kitchen rather than a factory running one process.

AIGary Marcus plans to testify at a New York City Council hearing on AI policy, urging the council to support a bill requiring third-party validation of AI models. He argues for an FDA-like independent review regime, with developers demonstrating that benefits outweigh risks before market access, and for stronger whistleblower protections.

AIRoon dismisses the idea of an inner ring of effective altruists that are on track to become trillionaires, Oxford professors, or powerful political lobbyists. The post responds to an EA Forum essay titled "You can't join the secret inner circle of cool effective altruists" by ozymandias.

AIBoris Power, who is tied to OpenAI, says Shopify is well positioned to be one of the biggest winners, alongside sellers themselves. The post gives no specifics on what drives this advantage. A reply from @tobi about hearing many similar stories provides only background.

AIBoris Power says GPT-6 can work autonomously on 3D design for hours while its results keep improving, a gap other models failed to match because they could not recover from mistakes. Design Arena reports GPT-6 Astra took #1 on four leaderboards, including 3D Design at 1484 and Frontend at 1397, a month after release.

AIWill Depue, an OpenAI-affiliated account, says his conviction has grown that scarce data becomes extremely valuable as models approach narrow superintelligence. He is responding to a quoted post arguing that over 90% of the economy trades below the value of its tokens.

AIBoris Power, OpenAI's account, posted a playful emoji-only message that drew attention to OpenAI's model naming. The quoted post traces the sequence from GPT-1 through GPT-6.1 Sol, including the o-series, Codex suffixes, and the Sol, Terra, and Luna names.

AIJoshua Achiam announces a talk at The Curve in 15 minutes in Eigen, covering the acceleration emergency and a policy agenda for superintelligence's wide-ranging impacts.

AIVercel completed migrating Turborepo from Go to Rust, which Rauch says was chosen for better low-level OS access despite controversial returns on human migration costs. He argues that what is best for humans is no longer necessarily best for business now that agents are writing code, and suggests Rust may not be the final toolchain.

AIJoshua Achiam observes that extreme detail in a graphic, once a plausible sign of quality and effort, now reads as an aesthetic marker of AI-generated slop. The post offers no specific tools or examples, only this reversal in how audiences perceive detail.

AIDemis Hassabis says he is proud of Google's work using AI to accelerate science and medicine for society's benefit. The quoted post from Sundar Pichai highlights recent examples, including the open AlphaGenome Atlas mapping 9B possible single-letter genetic changes and the WeatherNext 3 global weather model. It also points to translation services now available in nearly 300 languages.

AIGuillermo Rauch says his new project has a hand-written README for human readers, while its internal documentation is written in AI-style English for agents. He argues that blogs, tweets, and READMEs are human communication and should be written by people to connect with other readers.

AIJerry Liu says ChatGPT/Codex currently has the best agent interface for deep work, unifying coding and knowledge work in one place with forking support that Claude's app lacks. He still prefers Claude Code CLI as close to the best a CLI can be, and uses Opus 5.5 mainly through it for product demos, while noting a GUI is sometimes nicer.

AIA satirical weekly cycle shows developers rebuilding their workflows each time a new model drops, with the post advising them to hold workflows loosely and fundamentals tightly. The post contains no product names, versions, or benchmark figures.

AIKylie Robison commented that the timeline is extremely dumb, reacting to reports that Elon Musk announced SpaceXAI will officially change its name to SpaceXSI. The post itself gives no further details about the rename.

AIThe poster calls GPT-6.1-Sol their go-to model for both work and personal use, saying it is "all you need." Citing Arena's real-usage cost-per-task data, they claim users should get about 5x more usage from GPT-6.1-Sol than from Astra.

AIJason Liu posted that an "autistic Chinese dad" has been achieved internally, with no further details given. The post appears to be a joke, and it is quoted alongside a viral tweet describing an AI tool that flagged unrelated products for "bird imagery."

AIA developer ported Muse's gadget client to C so it runs natively on a PSP that had sat in their house for over 15 years. Holding R and speaking into the built-in mic lets Muse answer, with OpenAI providing the voice. The main post, from Alexandr Wang, reacts to the project with a short remark about nostalgia.

AINVIDIA's Bryan Catanzaro says players testing DLSS 5 show that neural rendering has redefined real-time graphics, calling it the payoff of ten years of dedicated research and development. He frames the change as "5 years of graphics progress in one toggle," linking to a video demonstration.