trending now
quality: all 6+ 8+
3
0

nah is a context-aware permission guard for Claude Code that uses deterministic command classification to enforce fine-grained policies (allow/context/ask/block) on tool calls, preventing unintended file deletion, key exfiltration, and malware installation without requiring manual deny-list maintenance.

github.com · schipperai· 22 days ago · tool · details · hn 123
7
0
appsec.space · _zeta· 8 days ago · 11 min · news · details · hn 1
2
0
infosecwriteups.com · Ehtesham Ul Haq· 8 days ago · 5 min · tutorial · details
0
thehackernews.com · [email protected] (The Hacker News)· 8 days ago · exploit · details
0
securelist.com · Kaspersky Security Services· 8 days ago · details
0
0
blog.trailofbits.com · trailofbits· 8 days ago · 9 min · web3 · details
this feed is available as an API
GET /api/v1/news/?min_rating=7&days=1
1
0

The author argues that OpenAI's charter contains a self-sacrifice clause committing to halt competition if competitors achieve AGI first, yet Sam Altman's publicly stated AGI timelines have continuously accelerated (from ~2033 in 2023 to ~2025 in recent statements) while OpenAI's GPT-5.4 trails competitors like Claude and Gemini in capability benchmarks, suggesting OpenAI should be joining forces with competitors per its own stated policy but continues racing instead.

mlumiste.com · skandium· 25 days ago · 3 min · opinion · details · hn 404
1
0

LibreOffice 26.2 release announcement highlighting new Markdown import/export support, performance improvements, and enhanced compatibility with proprietary office formats.

blog.documentfoundation.org · todsacerdoti· 25 days ago · 5 min · news · details · hn 404
5
0

This article describes how Quint, a formal specification language, was used to validate and guide LLM-assisted code generation for a significant consensus protocol change (Tendermint to Fast Tendermint) in the production Malachite BFT system. The approach uses executable specifications as validation points between English descriptions and implementation, enabling model-based testing to transfer confidence from spec to code.

quint-lang.org · mempirate· 22 days ago · 12 min · research · details · hn 102
7
0
arxiv.org · matt_d· 10 days ago · 4 min · research · details · hn 2
0
johnnymetz.com · johnnymetz· 10 days ago · 6 min · security · details · hn 2
1
0

A profile of physicist Astrid Eichhorn and her work on asymptotic safety, a theory proposing that quantum gravity becomes self-similar and fractal-like at the Planck scale, offering an alternative to string theory and loop quantum gravity.

quantamagazine.org · tzury· 22 days ago · 18 min · news · details · hn 131
7
0
0
welivesecurity.com · welivesecurity· 8 days ago · 8 min · threat · details
1
0

This is a financial commodity price tracking page for urea fertilizer with historical data, price charts, and market forecasts. It contains no security-related content.

tradingeconomics.com · burnt-resistor· 22 days ago · 5 min · not-security-related · details · hn 111
1
0

This article is not security-related. It appears to be a link to an archived opinion piece about spelling and grammar standards among elites, with no technical or security content.

wsj.com · matthieu_bl· 22 days ago · opinion · details · hn 126
1
0

A chemical engineer built a vanilla JavaScript refinery simulator game to visualize downstream operations (desalting, distillation, hydrotreating, cracking, blending) for education purposes, sharing technical lessons on LLM-assisted development, physics-to-CSS mapping, mobile event handling, and state management in large single-page apps.

fuelingcuriosity.com · fuelingcurious· 22 days ago · 3 min · tool · details · hn 123
7
0
download.ssrn.com · droidjj· 10 days ago · research · details · hn 2
0
page 76 of 279
news.rdintel.com · api · mcp · rdintel.com