The best Hacker News stories from All from the past day
Latest posts:
Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor
Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor
Grok CLI uploaded the whole home directory to GCS
<a href="https://xcancel.com/a_green_being/status/2076598897779020159" rel="nofollow">https://xcancel.com/a_green_being/status/2076598897779020159</a>
LAPD lets contract with surveillance giant Flock expire
How to read more books
A graph that should be front-page news
Ask HN: What Are You Working On? (July 2026)
What are you working on? Any new ideas that you're thinking about?
Ask HN: Add flag for AI-generated articles
Should HN add the ability to flag articles as AI-generated? This doesn't have to act as a regular flag, i.e., it won't de-rank the article; it could just show up as an indicator, allowing others (like myself) who don't like reading AI-generated text, to skip it.<p>Open questions:<p>1. Why is the regular voting system not enough?<p>2. Should HN change in response to the gen AI era? It has been successful not changing fundamentals.
Zig Creator Calls Spade a Spade, Anthropic Blows Smoke
Mesh LLM: distributed AI computing on iroh
Since Chromium 148, Math.tanh is now fingerprintable to link underlying OS
Vint Cerf, “father of the Internet”, is retiring
I love LLMs, I hate hype
Prefer strict tables in SQLite
Nvidia, CoreWeave, and Nebius: Inside the Circular Financing of the GPU Boom
Old and new apps, via modern coding agents
What xAI's Grok build CLI sends to xAI: A wire-level analysis
Under federal rule, colleges must leave grads better off or lose financial aid
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
This started based off of a hunch. We usually use OpenCode, but were 'forced' to use Claude Code for a while due to issues with Meridian. In that time, we saw the usage meter rise much, much more quickly than when using OpenCode.<p>This was the initial anecdotal evidence, but we undertook this small study to collect empirical data:<p>We added logging between the agentic coding tool (Claude Code and OpenCode) and Anthropic's endpoint, and captured all requests (and the returned usage blocks).<p>With one caveat (toward the end of the post) we found unambiguously that Claude Code was far more inefficient in terms of its cache strategy and its harness token usage than OpenCode.
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
This started based off of a hunch. We usually use OpenCode, but were 'forced' to use Claude Code for a while due to issues with Meridian. In that time, we saw the usage meter rise much, much more quickly than when using OpenCode.<p>This was the initial anecdotal evidence, but we undertook this small study to collect empirical data:<p>We added logging between the agentic coding tool (Claude Code and OpenCode) and Anthropic's endpoint, and captured all requests (and the returned usage blocks).<p>With one caveat (toward the end of the post) we found unambiguously that Claude Code was far more inefficient in terms of its cache strategy and its harness token usage than OpenCode.