NewsForest

Japan develops a method to recover up to 90% of lithium from used EV batteries 500 by donohoe | 124 comments on Hacker News.

Building and shipping Mac and iOS apps without opening Xcode 465 by speckx | 202 comments on Hacker News.

Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor 463 by get-inscribe | 185 comments on Hacker News.

Modern decor may be straining people's brains 264 by downwithdisease | 254 comments on Hacker News.

Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k 299 by systima | 171 comments on Hacker News. 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. This was the initial anecdotal evidence, but we undertook this small study to collect empirical data: 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). 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.

Female US rower completes historic solo journey from California to Hawaii 311 by speckx | 104 comments on Hacker News.