Blog

ayghri/i-have-adhd: A skill to stop your coding agent from burying the answer. ADHD-friendly output. ยท GitHub

ayghri/i-have-adhd: A skill to stop your coding agent from burying the answer. ADHD-friendly output. ยท GitHub

๐Ÿš€ Explore this awesome post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: โœ… **What Youโ€™ll Learn**: ADHD-friendly outputs. No ADHD diagnosis needed! ๐Ÿ‡ฌ๐Ÿ‡ง ยท ๐Ÿ‡จ๐Ÿ‡ณ ยท ๐Ÿ‡ง๐Ÿ‡ท ยท ๐Ÿ‡ฏ๐Ÿ‡ต ยท ๐Ÿ‡ป๐Ÿ‡ณ ยท ๐Ÿ‡ฐ๐Ÿ‡ท ยท ๐Ÿ‡น๐Ÿ‡ญ Copy/paste into your CLI prompt: Install the i-have-adhd skill/plugin from https://github.com/ayghri/i-have-adhd, refer to the repo's AGENTS.md for instructions. Or ๐Ÿ”— check the installation instructions. A skill for your coding assistant that stops it from burying the answer. Action first. Steps numbered. No "Hope this helps!" Great question! Let me think about this. Your auth flow has a few moving pieces: the middleware, the token verification, and…
Read More
Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses

Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses

โœจ Explore this must-read post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: โœ… **What Youโ€™ll Learn**: How much GPU RAM do you actually need to run Qwen3.8 27B without sacrificing quality? The full BF16 model weighs 55 GB, putting it beyond most consumer hardware. Yet the 17 GB Q4_K_M matches the full model on a popular agentic coding benchmark, Terminal-Bench 2.1. It fits on a 24 GB card such as RTX 4090, still leaving room for about 64k tokens of context. Compression eventually hits a cliff. At 1 bit, the model performs around random chance on GPQA Diamond, and longer reasoning…
Read More
TWEET and the Bird Logo Apparently Enter the Public Domain, But X Maintains Its Grip on the TWITTER Mark (For Now)-X v. Project Bluebird

TWEET and the Bird Logo Apparently Enter the Public Domain, But X Maintains Its Grip on the TWITTER Mark (For Now)-X v. Project Bluebird

๐Ÿ’ฅ Check out this insightful post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: โœ… **What Youโ€™ll Learn**: This case involves Project Bluebird, a social media service previously named โ€œtwitter.newโ€ and renamed to tweet.app immediately after this ruling (for reasons this post makes obvious). Project Bluebirdโ€™s service is designed to reimagine the Twitter service that Musk imploded when he morphed Twitter into X. Project Bluebird claims X has abandoned the TWITTER, TWEET and Bird Logo trademarks. In 2025, Project Bluebird filed ITU applications for TWITTER and TWEET. Citing the following evidence, the court says X hasnโ€™t abandoned the TWITTER marks: X Corp.โ€™…
Read More
On Really Trying ยท Gwern.net

On Really Trying ยท Gwern.net

๐Ÿš€ Read this trending post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: ๐Ÿ“Œ **What Youโ€™ll Learn**: What are the true limits to motivation? The Programmersโ€™ Credo: we do these things not because they are easy, but because we thought they were going to be easy Maciej Cegล‚owski Student: How can one realize his Self-nature? I know so little about the subject. Yasutani: First of all, you must be convinced you can do so. The conviction creates determination, and the determination zeal. But if you lack conviction, if you think โ€œmaybe I can get it, maybe I canโ€™tโ€, or even worse, โ€œThis…
Read More

On the Navierโ€“Stokes Millennium Prize Problem

โœจ Check out this must-read post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: ๐Ÿ“Œ **What Youโ€™ll Learn**: On the Navierโ€“Stokes Millennium Prize Problem (via) Impressive result from OpenAI, who used an unreleased model to produce a resolution to the Navierโ€“Stokes existence and smoothness problem, one of the seven Millennium Prize Problems that have been subject to a $1,000,000 prize since May 24th, 2000. The discovery is somewhat overshadowed by accusations of skulduggery from Tristan Buckmaster, an NYU mathematics professor who was collaborating on related problems with Levent Alpรถge, an accomplished mathematician who currently works for Anthropic. Tristan's complaint accompanied a hastily…
Read More
A Biography of Lee Holloway, the Architect of Cloudflare’s Technology (Part 1)๏ฝœๅ ้ƒจ้›…ไธ€ใ€€masakazu urabe

A Biography of Lee Holloway, the Architect of Cloudflare’s Technology (Part 1)๏ฝœๅ ้ƒจ้›…ไธ€ใ€€masakazu urabe

๐Ÿš€ Discover this insightful post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: ๐Ÿ“Œ **What Youโ€™ll Learn**: Cloudflare's rapid growth as a cloud service is due in part to its many unique technologies. Technologies like Anycast and same-IP access are just a few examples, and it was CTO and co-founder Lee Holloway who created these mechanisms. However, he was forced to step down due to a serious brain disease (FTD). This article explores the technological achievements he left behind and the tragedy of the illness that came to light. Text by Masaichi UrabeBorn into an Apple FamilyLee Holloway was born in California,…
Read More
Introducing AlphaGenome Atlas

Introducing AlphaGenome Atlas

๐Ÿ”ฅ Discover this insightful post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: ๐Ÿ’ก **What Youโ€™ll Learn**: The human genome is made of about 3 billion base pairs of DNA โ€” but much of it remains a mystery. Scientists understand the 2% of the human genome that codes for proteins relatively well, but have only limited knowledge of the remaining 98%. Our AlphaGenome model has already shown how single changes in these non-coding DNA regions can disrupt molecular processes like protein production, but the bigger picture remained unclear.Today, we're introducing AlphaGenome Atlas, a database that predicts the effects of every possible single…
Read More

LLM Attention Visualization

๐Ÿ’ฅ Check out this insightful post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: โœ… **What Youโ€™ll Learn**: One interesting thing about transformer-based large language models are that, during the generation phase, it is able to draw information from any of its previous tokens. But it needs to be selective; if every token affects the generation equally, it won't be very effective. This process needs a mechanism to decide how much a token affects the next token.Turns out, we can visualize this mechanism!You can tap or hover over any of the generated tokens to see the past tokens that affected* the generation.…
Read More
Harvard study predicts most suicide attempts a week in advance

Harvard study predicts most suicide attempts a week in advance

๐Ÿš€ Discover this must-read post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: ๐Ÿ“Œ **What Youโ€™ll Learn**: As a leading researcher on suicide,ย Matthew K. Nock knows the subjectโ€™s grim statistics by heart. Suicide is the second-leading cause of death for Americans aged 10 to 34, trailing only accidents. It claims more lives around the world each year than war, genocide, homicide, and all other violence combined. And 50 percent of people who died by suicide saw a clinician in their final month, according to multiple studies in recent decades, includingย Nockโ€™s own research.For Nock, that last statistic is both agonizing and motivating. Some…
Read More
argonautlabsai/deltafin: ARGODRIVE Deltafin: Kimi K3 (2.8T MoE) streamed from SSDs on Apple Silicon โ€” fork of gavamedia/deltafin with the ARGODRIVE storage work and benchmark package ยท GitHub

argonautlabsai/deltafin: ARGODRIVE Deltafin: Kimi K3 (2.8T MoE) streamed from SSDs on Apple Silicon โ€” fork of gavamedia/deltafin with the ARGODRIVE storage work and benchmark package ยท GitHub

๐Ÿ”ฅ Explore this must-read post from Hacker News ๐Ÿ“– ๐Ÿ“‚ **Category**: ๐Ÿ“Œ **What Youโ€™ll Learn**: TL;DR โ€” Kimi K3 (2.8T-parameter MoE, 1.45 TB of expert weights) running on one M5 Max MacBook Pro with 128 GB, experts streamed from four SSDs. 1.00 tok/s steady decode over a 512-token answer; 1.13 over 128; 0.96 on the public 17-token prompt (upstream reported 0.68). The honest limit: a 512-token prompt takes ~6.3 minutes to its first token. Cause found (prefill re-reads each layer's experts 8ร—), fix planned, not built. Useful findings: one drive gives โ‰ˆ52% of four-drive speed, two โ‰ˆ73%, three โ‰ˆ90% โ€”…
Read More