Link Sharing

Link Sharing

56616 bookmarks
Newest
Andyyyy64/whichllm: Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
Andyyyy64/whichllm: Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm
·github.com·
Andyyyy64/whichllm: Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
DeepSeek V4 Pro beats GPT-5.5 Pro on precision
DeepSeek V4 Pro beats GPT-5.5 Pro on precision
DeepSeek V4 Pro wins this head-to-head by being more exact where it matters: following instructions, matching schemas, and solving edge cases cleanly. GPT-5.5 Pro is still strong, but it gave away points with avoidable deviations.
·runtimewire.com·
DeepSeek V4 Pro beats GPT-5.5 Pro on precision
Token Spend Out of Control? The Case for Smarter Routing
Token Spend Out of Control? The Case for Smarter Routing
To understand how teams keep this under control in production, we sat down with Scott Breitenother and Sid Sijbrandij, co-founders of Kilo, an open-source coding agent that runs through a lot of these loops every day.
·blog.bytebytego.com·
Token Spend Out of Control? The Case for Smarter Routing
The EU Open Source Strategy
The EU Open Source Strategy
The EU Open Source Strategy places open source at the centre of the EU’s technological sovereignty by promoting European open alternatives to non-EU proprietary solutions in critical domains.
·digital-strategy.ec.europa.eu·
The EU Open Source Strategy
Everything Apple Announced at WWDC 2026
Everything Apple Announced at WWDC 2026
Updates include a new souped-up Siri, lots of iOS enhancements, and some inkling on how an AI partnership with Google has come to power Apple’s products.
·wired.com·
Everything Apple Announced at WWDC 2026
Trust Factory
Trust Factory
“We’re accumulating code faster than we are accumulating trust.” Sometimes a phrase just hits.
·tidyfirst.substack.com·
Trust Factory
How LLMs Actually Work
How LLMs Actually Work
A from-the-ground-up walkthrough of how modern LLMs work, from tokens to transformer blocks to the next-token loop
·0xkato.xyz·
How LLMs Actually Work
The Blight Reaches Microsoft: 73 Repos Disabled in 105 Seconds
The Blight Reaches Microsoft: 73 Repos Disabled in 105 Seconds
GitHub disabled 73 Microsoft repositories across four of its GitHub organizations — the entire Azure Functions org, the whole Durable Task family, and a row of AI sample apps — in a 105-second sweep on June 5. The recompromised durabletask package sits at the center, and the fingerprints point at the open-sourced Miasma worm.
·opensourcemalware.com·
The Blight Reaches Microsoft: 73 Repos Disabled in 105 Seconds
State of Agentic AI Security and Governance 2.01
State of Agentic AI Security and Governance 2.01
The State of Agentic AI Security and Governance provides a comprehensive view of today’s landscape for securing and governing autonomous AI systems. It explores the frameworks, governance models, and global regulatory standards shaping responsible Agentic AI adoption. Designed for developers, security professionals, and decision-makers, the report serves as a practical guide for navigating the complexities […]
State of Agentic AI Security and Governance 2.01
·genai.owasp.org·
State of Agentic AI Security and Governance 2.01
Life is too short for a slow terminal
Life is too short for a slow terminal
I do all my work in the terminal, so it has to be quick. How my zsh starts in 30 milliseconds without a framework, and how to measure where your own shell spends its time.
·mijndertstuij.nl·
Life is too short for a slow terminal