New comment by mattbaconz in "Show HN: Apple's SHARP running in the browser via ONNX runtime web"

mattbaconz — Tue, 05 May 2026 01:48:36 +0000

2.4GB in browser is crazy. I’m curious whether quantization works here or if the model quality falls apart too much.

New comment by mattbaconz in "Anthropic Nerfed Opus 4.6 Before the 4.7 Launch"

mattbaconz — Sat, 18 Apr 2026 04:15:12 +0000

The article splits three things: default behavior (adaptive thinking, effort), UI redaction of reasoning, and whether external benchmark charts are comparable. For people who live in Claude Code daily: did you notice the read-before-edit shift or more “edit without context” before 4.7, and was visible thinking part of how you debugged failures?

Hacker News: mattbaconz

New comment by mattbaconz in "Show HN: Apple's SHARP running in the browser via ONNX runtime web"

New comment by mattbaconz in "Anthropic Nerfed Opus 4.6 Before the 4.7 Launch"