Guest : Login | Sign up
LSCPPDEV

LATEST FROM THE BLOG

Practical Linux, AI and tech.

2026-11-15

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 Metropolitan Police Agency and gave them the full method. How the scheme worked Han described it plainly. He used a microcamera to photograph the test questions, sent the images to an AI, and checked the answers on his smartphone. That is the whole trick. No zero-day, no fancy radio gear, no insiders. A consumer camera, a phone and a chatbot were enough to break one of Asia's most credential-obsessed exams, in real time, across two rounds. The exam body's existing defenses, presumably built for the cheating technology of a decade ago, never had a chance against a pipeline that reads and answer...

Read the full post →
2026-11-15

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...

Read post →
2026-11-14

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, ...

Read post →
2026-11-14

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 Extens...

Read post →
2026-11-13

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 appoin...

Read post →

AI FOUNDATIONS

Practical questions.

Which AI setup do I actually need?

Start with one agent unless you have a measured reason to use more. Compare local and hosted options by hardware cost, latency, reliability and the time you spend reviewing output. Add orchestration only when separate jobs genuinely need separate ownership, memory or permissions.

How do I secure an AI agent?

Give the agent the smallest possible access: isolated files, least-privilege credentials and approval gates for external actions. Treat web pages and documents as untrusted input, test known failure cases, and require a human before publishing, deleting or sending.

How do I review AI-written code without losing ownership?

Keep diffs small, read the changes, run meaningful tests and investigate failures instead of accepting repeated rewrites. Manually handle the critical path and make the agent explain its assumptions. If you cannot explain or verify the change, do not ship it.

Subscription AI or local models: which is cheaper?

Compare total workload, not headline price. Include usage limits, reliability, hardware and electricity, model download size, speed and the value of your review time. Local models make sense when privacy, predictable cost or offline use matters; hosted models can be simpler for occasional or bursty work.

BUILT HERE

Linux apps.

01 / LINUX APP

HiveMind

A self-hosted team of always-on AI agents for Linux. Create named teammates, message them like colleagues, and hand off real work — each agent runs in its own rootless ...

View project →
02 / LINUX APP

Daedalus

C++23 autonomous AI-agent library — one monorepo with its two host apps: monkeybyte, the GTK code editor, and icarus, the terminal agent. Ships as libdaedalus.a; embed ...

View project →
03 / LINUX APP

ChimpFlow

Local TTS voice service for Linux — API-key auth, dark web admin UI, and an OpenAI-compatible speech endpoint. Speech-to-text is on the way.

View project →
04 / LINUX APP

lsPass

Local, encrypted password manager. No network, no cloud, no telemetry — nothing secret ever touches disk in plaintext.

View project →

Linux install packages will appear here as they become available.

APPS

Download for Linux

Desktop tools, utilities and local-first software.

DEVELOPMENT

Libraries and engines

Daedalus, OmniNet, vortxGE, golnn, monkeybyte and icarus.

SEE WHAT'S RUNNING

HiveMind in action.

FEATURED PROJECT / HIVEMIND● ACTIVE
HIVE
SERVER
UBUNTU
WORKER
SYDNEY
WORKER
BOBwebsites
HONEYBEEresearch
FORGEmedia
BUZZnews
QUEENBEEmusic
SCOUTcoordination

ONLINE six agents reporting

Sitemap