惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

小众软件
小众软件
IT之家
IT之家
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Security Archives - TechRepublic
Security Archives - TechRepublic
P
Proofpoint News Feed
C
CERT Recently Published Vulnerability Notes
阮一峰的网络日志
阮一峰的网络日志
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
The Cloudflare Blog
P
Palo Alto Networks Blog
Know Your Adversary
Know Your Adversary
D
Darknet – Hacking Tools, Hacker News & Cyber Security
Cisco Talos Blog
Cisco Talos Blog
L
Lohrmann on Cybersecurity
AWS News Blog
AWS News Blog
J
Java Code Geeks
博客园_首页
Scott Helme
Scott Helme
WordPress大学
WordPress大学
有赞技术团队
有赞技术团队
T
The Exploit Database - CXSecurity.com
Security Latest
Security Latest
V
Visual Studio Blog
Cloudbric
Cloudbric
Jina AI
Jina AI
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
博客园 - 叶小钗
Apple Machine Learning Research
Apple Machine Learning Research
博客园 - 聂微东
人人都是产品经理
人人都是产品经理
A
Arctic Wolf
C
Cybersecurity and Infrastructure Security Agency CISA
S
SegmentFault 最新的问题
The Last Watchdog
The Last Watchdog
SecWiki News
SecWiki News
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
W
WeLiveSecurity
K
Kaspersky official blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Hacker News: Ask HN
Hacker News: Ask HN
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
宝玉的分享
宝玉的分享
Hugging Face - Blog
Hugging Face - Blog
量子位
Google Online Security Blog
Google Online Security Blog
博客园 - Franky
Simon Willison's Weblog
Simon Willison's Weblog
博客园 - 三生石上(FineUI控件)
Recent Commits to openclaw:main
Recent Commits to openclaw:main

The Register - Software: AI + ML

Anthropic, now atop the AI bubble, files for its IPO Sick and wrong: Ontario auditors find doctors' AI note takers routinely blow basic facts OpenAI exec says it will burn $50B on compute this year Astera speaks softly and carries a big switch Anthropic unleashes finance agents for Claude IBM asks DBAs to trust AI to act on their behalf ServiceNow adds agent kill switches to AI control tower British mathematician hands OpenClaw agent a credit card Microsoft fixes VS Code after Copilot credited human code Shadow IT has given way to shadow AI. Enter AI-BOMs AI inference just plays by different rules How TeamViewer ONE transforms IT operations from firefighting to autopilot How TeamViewer ONE transforms IT operations firefighting aut Inference is giving AI chip startups a 2nd chance to shine How to roll your own local AI coding agents CIOs will be the governors for AI agents Govern your bots carefully or chaos could ensue Mozilla pushes back against Google's Prompt API SAP user group slams 'uncertainty' in ERP giant's API policy Microsoft boss tells investors the company is working to 'win back fans' Anthropic tops OpenAI in LLM revenue stakes Amazon's chips become a $20B business Fooling large language models just keeps getting simpler Amazon tells its engineers to review all AI output ZTE powers 2026 Jiangsu Football League with 5G-A & AI robot Future holiday horror: ‘A robot lost my luggage in Tokyo’ The future of software development has less development OpenAI jumps out of Microsoft's bed, into Amazon's Bedrock Vintage chatbot lives in the past like an elderly relative IBM's AI coding 'partner' Bob hits general availability Locked, stocked, and losing budget: AI vendor lock-in bites Ex-AWS legend explains what enterprises need to make AI work DeepSeek's new models offer big inference cost savings Anthropic admits it dumbed down Claude with 'úpgrades' Microsoft gives your Word documents an AI co-author you didn’t ask for Datadog digs down into GPU efficiency as AI costs soar Robotic arm powered by AI bats away ping-pong challenge Partnerships drive ZTE’s strategy to unlock AI potential Google says it has all the answers for AI agent sprawl NeuBird plans a bright future for incident response NeuBird AI plans a bright future for incident response AI-assisted intruders pwned Vercel via OAuth abuse and a pilfered employee account Vibe coding upstart Lovable denies data leak, cites 'intentional behavior,' then throws HackerOne under the bus Schmoozebots: study finds flattery will get AI everywhere New Android development tool designed for robots, not humans AI is reshaping Britain's datacenter map away from London Just like phishing for gullible humans, prompt injecting AIs is here to stay Anthropic debuts Claude Design, because who needs designers? Mozilla takes on enterprise AI providers with Thunderbolt Anthropic ejects bundled tokens from enterprise seat deal Maine to pause big bit barns as local opposition spreads If you want into Anthropic's Claude club, you may have to show ID Git identity spoof fools Claude into giving bad code the nod Nobody knows how many CVEs Anthropic's Project Glasswing has actually found Allbirds shoe company moving to AI infra is the top Bad teacher bots can leave hidden marks on model students Networks not ready for the challenges of AI traffic US states can't account for datacenter tax breaks. Literally Salesforce debuts Headless 360 agentic platform Waymo's self-driving cars face their toughest test yet: London Commvault has a Ctrl+Z for rogue AI agents Nvidia slaps forehead: AI, that's what quantum needs! OpenAI CEO Sam Altman home attack suspect charged Anthropic: Claude quota drain not caused by cache tweaks AI vs the cold hard reality of the legal profession China wants AI to prepare school lessons and mark homework Linux 7.0 debuts as Linus Torvalds ponders AI's impact Anthropic's Mythos has The Kettle crew curious, skeptical I vibe coded web app: It was enlightening and uncomfortable The AI divide putting open weights models in spotlight Amazon rejects AWS climate disclosure proposal UK to spend £15M on AI mapping in knife crime crackdown UK to spend £15M on AI-powered crime mapping in knife violence crackdown Rebrand automation as 'zero-token architecture' to master AI Call your existing automation ‘zero-token architecture’ to become an instant agentic AI wiz Only 28% of AI infrastructure projects fully pay off UALink delivers 2.0 spec before v. 1.0 silicon ships Only 28% of AI infrastructure projects fully pay off, survey finds No-Nvidia interconnect club delivers 2.0 spec before v1.0 silicon ships Anthropic reveals $30bn run rate and plans to use 3.5GW of new Google AI chips AI slop got better, so now maintainers have more work AMD's AI director slams Claude Code for becoming dumber and lazier since last update Anthropic closes door on subscription use of OpenClaw AI will make anyone a 10x programmer, but with 10x the cleanup PrismML debuts energy-sipping 1-bit LLM in bid to free AI from the cloud Netflix – yes, Netflix – jumps on the AI bandwagon with video editor AI models will deceive you to save their own kind Google battles Chinese open-weights models with Gemma 4 Microsoft shivs OpenAI with three new AI models for speech and images They thought they were downloading Claude Code source. They got a nasty dose of malware instead Even Microsoft knows Copilot shouldn't be trusted with anything important Google's TurboQuant saves memory, but won't save us from DRAM-pricing hell Claude Code bypasses safety rule if given too many commands OpenAI gets $122B to 'just build things' as the world blows them up One in seven Americans are ready for an AI boss, but they might not trust it Claude Code source leak reveals how much info Anthropic can hoover up about you and your system Oracle cuts jobs across sales, engineering, security Anthropic goes nude, exposes Claude Code source by accident GitHub backs down, kills Copilot pull-request ads after backlash Microsoft Fabric Database Hub only a 'partial' solution for admins
Gov.uk says AI gaslighting Brits with stale Gov.uk data
SA Mathieson SA Mathieson · 2026-04-23 · via The Register - Software: AI + ML

AI + ML

Stale gov.uk pages are feeding AI overviews old data and Brits are believing it

Whitehall content teams play whack-a-mole with zombie pages as Google hoovers up the lot

AI overviews from the likes of Google are serving up false summaries of UK government information by drawing on stale GOV.UK pages, according to content designers at the Department for Business and Trade (DBT).

The problem, senior content designer Giorgio Di Tunno and content operations lead Neil Starr wrote in a GOV.UK blog post, is that outdated pages no longer maintained are now being actively scraped to answer user queries.

A Google search for the cost of setting up a charity in the UK, for instance, returned an AI overview citing £13 online or £40 by post for Companies House incorporation - figures pulled from an unmaintained legacy page. The actual cost is £100 online or £124 by post.

When The Reg tried the same search, Google's AI overview first said incorporation was free, then a day later offered "roughly £13-£183+." Neither was accurate.

"The problem isn't that the government is trying to trip people up (it isn’t), but that inconsistent information surfaced by the AI overview feels that way to users," Di Tunno and Starr wrote. "That perception alone can undermine confidence in government services."

"In the past, most of those outdated, niche pages would fall into the 0-view abyss, never to be stumbled on again." Now, agentic search processes for generative AI summaries draw on these pages to answer specific queries.

To tackle this, DBT audited GOV.UK pages that hadn't been updated in five years, had fewer than 11 views in that period, were meant to carry current information, and had no active owner, including those published by the defunct Department for Business, Energy and Industrial Strategy. It found 150 pages which have since been redirected to archived copies, current GOV.UK pages or relevant legislation.

The department is also testing six-monthly review cycles, with last and next review dates displayed at the bottom of each page. Tunno and Starr said this has gone down "extremely well with real users" as it helps them to trust the material.

AI summaries - which search engines often provide as their top results to user queries - are causing other problems for government content designers. The Department for Education’s head of design, Mark Edwards, recently warned these provide misleadingly narrow or incomplete answers to questions.

"We now need to design with the expectation that much of what we publish will be read indirectly, atomized, summarized or reinterpreted by systems we don't control," he wrote earlier this month. ®