Guest : Login | Sign up
LSCPPDEV

All Blog Posts

RSS Feed

He Scored 397.5 Out of 400. AI Did the Work.

Some stories are funny until you sit with them for a minute. A 34-year-old man named Han Won-seok sat South Korea's certified tax accountancy exam, one of the country's brutal professional gateways, and scored 397.5 out of 400 in the first round, getting exactly one of 160 questions wrong. The internet noticed. The score was too clean, the margin too perfect, and the speculation started immediately. On Sunday, Han confessed in a video posted to his lawyer's YouTube channel: he had cheated in both rounds, using a miniature camera, a mobile phone and generative AI. He also walked into the Seoul ...

Read more...

AI & Tech News — 2026-11-16

Sundays are for follow-ups, and this one has plenty. Nvidia's security posture is under a microscope, its ex-CEO has a petition behind him, and AMD keeps shipping kernel work. AMD posts patches for capacity-aware scheduling on hybrid CPUs AMD has published Linux kernel patches implementing capacity-aware scheduling for its hybrid processors, the kind that mix big and little cores. Getting the scheduler to place work on the right core for the right job is half the promise of hybrid silicon, and this is AMD putting kernel code behind it. Phoronix has the details. Source: https://www.phoronix.com...

Read more...

Italy's 805 Million Euro Message to Meta: Consent Is Not a Checkbox

On a normal news day, a €805 million fine would be the biggest tech story of the week. This week it had to queue behind a CEO resignation and a global cloud outage, which tells you something about the tempo we are living at. But the fine Italy's data protection authority dropped on Meta on Friday deserves attention, because it is a clean example of a regulator calling a bluff that Silicon Valley has run for a decade: the bluff that a single app-wide permission dialog constitutes informed consent. What Meta actually did The fine centers on a photo suggestion feature in the Facebook Android ap...

Read more...

AI & Tech News — 2026-11-15

A quieter Saturday, but the threads from this week keep pulling. Microsoft finished mopping up its global outage, AI agents got their own open-source browser, and the bill for last year's funding frenzy keeps arriving. Wine 11.22 can now emulate AVX on ARM64 The latest bi-weekly Wine release adds Advanced Vector Extensions support to its x86 emulation path on ARM64, which means modern Windows software that assumes AVX can now run nicely under ARM64EC builds. Wine 12.0 preparations are inching closer. If you run Windows apps on an ARM Linux machine, this is the release you have been waiting for...

Read more...

One Bad Day at Microsoft Stopped the World's Email

For most of Thursday and into Friday, a large chunk of the working world discovered what it actually runs on. Outlook stopped sending mail. Teams went dark. Copilot, Microsoft's AI assistant, fell over alongside the tools it is supposed to assist with. The UK's National Health Service told patients to keep their appointments but expect chaos, police forces asked the public to phone in crimes the old way, and schools from Glasgow to Melbourne lost their lesson platforms. At least 74 countries reported problems, and roughly 430 million people use these tools every day. One company's bad day beca...

Read more...

AI & Tech News — 2026-11-14

The Nvidia scandal stopped being about one man's judgment this week. New research says China's most powerful open-weight models were trained on chips Washington banned from export, and the story behind that is bigger than any keynote. Export-banned Nvidia chips are behind China's most powerful AI models Will DePue, a former OpenAI researcher now at the nonprofit Unemployment Labs, analyzed the weights of models openly released by DeepSeek, Moonshot AI, MiniMax and Ant Group, and found they still carry the configuration fingerprints of Blackwell GPUs, which are banned from export to China. His ...

Read more...

Jensen Huang Is Out: How Nvidia Lost Its CEO in Five Days

On Monday this blog covered the board investigation into Jensen Huang over an alleged affair with a suspected Chinese spy. By Thursday he was gone. Nvidia's board announced his resignation, CFO Colette Kress steps in as interim CEO, and more than $320 billion evaporated from the company's value in a day, over $600 billion for the week. Whatever you think of the man, the era he defined ended with a press release that did not even mention why. How it unwound in five days The sequence matters, because it shows an institution trying to digest a scandal faster than its own governance could handle. ...

Read more...

AI & Tech News — 2026-11-13

The biggest Nvidia story of the week did not come from a benchmark. Jensen Huang is out as CEO, and the fallout landed on the Linux driver, the open source world and the stock market all at once. Nvidia's Linux driver has a root problem, and 25 more disclosures are coming Security researchers at Stealthium published the first two of 27 NVIDIA driver vulnerabilities they have in the pipeline: ForgePtr (CVE-2026-47501) lets an unprivileged process in a GPU container go root on the host, and NvRoot (CVE-2026-47591) lets the GPU rewrite files the OS marked read-only from any tenant on the node. Bo...

Read more...

Synaptics Sends 125 Patents After One Developer's AI-Built Linux Driver

This week's running story is AI's collision with open source. On Monday a kernel maintainer quit reviewing because of the patch flood. On Wednesday, a different kind of blow landed: a company using patent law to kill an open source driver, one that happened to be written with an AI's help. What Vino was DisplayLink is Synaptics' proprietary system for pushing video over USB to docks and adapters. On Linux it has always been an uneasy fit: you need the vendor's closed-source software and the open EVDI kernel module beside it, and plenty of users find it flaky. Mike Lothian, who goes by FireBurn...

Read more...

AI & Tech News — 2026-11-12

The AI-and-open-source squeeze we have been tracking all week found a new target today, FreeBSD is polling its developers on an AI policy, and the Python world lost one of its founding minds. FreeBSD polls its developers on an AI policy The FreeBSD project published its Q3 2026 status report this week, and one line item stands out: the project is working to establish an official AI policy, shaped by polling its own developers first. That is a calmer route than the kernel's, where maintainers are drowning in AI-generated patches and policy got written after the flood arrived. Phoronix has the d...

Read more...

Sitemap