Site uses cookies to provide basic functionality.
Javascript rendering is set to off by default when visiting the site via .onion and .i2p domains. It can be enabled back again in user's settings section. Javascript rendering set to off means, that you can disable javascript in your browser now and the site will remain functional.
There is also IRC server now available via native IRC clients or non javascript web based one.
Fonts can be adjusted in user's settings section as well.
Check FAQ for more.

OK

Networks
Languages
1 2 3 5 8 11 17 25 37 54 79 116 171 250 366 392 393 394 395 396 535 537 786 900 1149 1151 1320 1436 1515 1570 1607 1632 1649 1661 1669 1675 1678 1681 1683 1684 1685 1686 ▲ ▼
I watched the State of the Union address to the nation by President Donald Trump on Tuesday night. I really enjoyed it. and thought it was an excellent showcase of Republican party priorities. as well as showing voters Trump’s vision for the future. heading towards the mid-term elections. I was shocked to hear that polls … Continue reading Trump’s State of the Union speech explains Republican values to mid-term voters →
Table of Contents Why Hardwood? Hello, Hardwood! Parsing Performance Built With AI, Not By AI What’s Next? Today, it’s my great pleasure to announce the first public release of Hardwood, a new parser for the Apache Parquet file format, optimized for minimal dependencies and great performance. Hardwood is open-source (Apache License 2.0) and supports Java 21 or newer. You can grab it from Maven Central and start p..
Table of Contents Why Hardwood? Hello, Hardwood! Parsing Performance Built With AI, Not By AI What’s Next? Today, it’s my great pleasure to announce the first public release of Hardwood, a new parser for the Apache Parquet file format, optimized for minimal dependencies and great performance. Hardwood is open-source (Apache License 2.0) and supports Java 21 or newer. You can grab it from Maven Central and start p..
Table of Contents Why Hardwood? Hello, Hardwood! Parsing Performance Built With AI, Not By AI What’s Next? Today, it’s my great pleasure to announce the first public release of Hardwood, a new parser for the Apache Parquet file format, optimized for minimal dependencies and great performance. Hardwood is open-source (Apache License 2.0) and supports Java 21 or newer. You can grab it from Maven Central and start p..
It‘s been a while since I‘ve written any blog posts. I‘ve been heads down on getting my blogging scripts updated the past 2 months. Quite a journey into writing CLIs, but I reached a milestone yesterday, I was able to successfully write a post using the new system. Still some things to figure out, but it means a much more streamlined process from writing words, to getting them onto the website, all via Github, with individual PRs for ea..
In December of 2023, due to carpal tunnel, I switched from my Happy Hacking Keyboard setup to a Kinesis Advantage 360. It’s been two years and change, and I haven’t looked back. Well, kind of.
In December of 2023, due to carpal tunnel, I switched from my Happy Hacking Keyboard setup to a Kinesis Advantage 360. It’s been two years and change, and I haven’t looked back. Well, kind of.
Cribsheet - ahalbert.com - 7 months ago - eng
Cribsheet: A Data-Driven Guide to Better, More Relaxed Parenting, from Birth to Preschool . By Emily Oster, PhD. 326 pages. Mommy forums are full of arguments about what is right and wrong for your child. What should your policy be for screen time? What’s the best way to approach potty training? Most of these arguments are based around ancedata. Worse, they often come with a lot of judgment attached to them. If you sleep train your baby,....
Cribsheet - ahalbert.com - 7 months ago - eng
Cribsheet: A Data-Driven Guide to Better, More Relaxed Parenting, from Birth to Preschool . By Emily Oster, PhD. 326 pages. Mommy forums are full of arguments about what is right and wrong for your child. What should your policy be for screen time? What’s the best way to approach potty training? Most of these arguments are based around ancedata. Worse, they often come with a lot of judgment attached to them. If you sleep train your baby,....
Synthetic Friction - june.kim - 7 months ago - eng
The Brave Search API now offers Place Search—a fast, granular endpoint for discovering businesses, landmarks, and more across over 200 million points of interest.
Synthetic Friction - june.kim - 7 months ago - eng
Your RAG answered correctly yesterday. Today, it contradicts itself. Nothing obvious changed — except the index. Retrieval drift is silent, cumulative, and rarely audited. This piece explains how to make it observable and reproducible - what must be versioned beyond vectors, how to enable point-in-time reconstruction, and when lightweight metadata is enough. Includes practical tracing patterns, replay strategies, and a risk-based decision g..
Your RAG answered correctly yesterday. Today, it contradicts itself. Nothing obvious changed — except the index. Retrieval drift is silent, cumulative, and rarely audited. This piece explains how to make it observable and reproducible - what must be versioned beyond vectors, how to enable point-in-time reconstruction, and when lightweight metadata is enough. Includes practical tracing patterns, replay strategies, and a risk-based decision g..
As AI reshapes the software landscape, SaaS companies face a new reality: Incremental improvements are no longer enough. In this episode of the Executive Guidance podcast, Pablo Dominguez of Insight Partners joins Jeff Gangemi to discuss how AI-first thinking, a culture of builders, and centralized strategy are redefining growth.
In today’s crowded media landscape, creating great content is only half the battle: Getting it in front of the target is what drives growth. In this episode of the Executive Guidance podcast, Noah Greenberg, Co-founder and CEO of Stacker, joins Jeff Gangemi, Toptal’s Growth and Digital Marketing Practice Lead, to discuss how data-driven storytelling and brand authority help brands scale reach, credibility, and impact.
To understand my point, I need to first explain three different cryptography attack papers / blog posts. I promise this won’t be boring. Three Little Disclosures Misuse-Prone Ciphers For All In a blog post titled Carelessness versus craftsmanship in cryptography, cryptography analyst and Queer in Cryptography emcee Opal Wright delves into the misuse-prone and side-channel-riddled […]
Hello! We're very glad to inform you that a new Eddie Air client version has been released: 2.25 beta. It is ready for public beta testing. How to test our experimental release: Go to download page of your OS Click the button Switch to EXPERIMENTAL Download and install This is a new version of Eddie Desktop (Windows / Linux / MacOS). The primary purpose of this release is to address several specific issues, including a significant CV....
Hello! We're very glad to inform you that a new Eddie Air client version has been released: 2.25 beta. It is ready for public beta testing. How to test our experimental release: Go to download page of your OS Click the button Switch to EXPERIMENTAL Download and install This is a new version of Eddie Desktop (Windows / Linux / MacOS). The primary purpose of this release is to address several specific issues, including a significant CV....
My favorite Ratio Christi person of all is Eric Chabot. He works at Ohio State University. He is the best. because can teach on many topics. he gets the best speakers to lecture. and mentors the most promising Christian students. I could tell you so many stories about his achievements as a Christian. Anyway. he … Continue reading The best argument against Islam is the historicity of Jesus’ death →
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
NVIDIA artificially restricts peer-to-peer (P2P) GPU communication to their enterprise cards. Turns out this is a software limitation, not a hardware one. I patched my drivers to remove it, hacked vLLM to take advantage of it, and got a 15-50% throughput improvement running Qwen 3.5 35b on dual RTX 3090s.
1 2 3 5 8 11 17 25 37 54 79 116 171 250 366 392 393 394 395 396 535 537 786 900 1149 1151 1320 1436 1515 1570 1607 1632 1649 1661 1669 1675 1678 1681 1683 1684 1685 1686 ▲ ▼
89 visitors online