Hacker News: speu

New comment by speu in "China’s open-weights AI strategy is winning"

speu — Mon, 20 Jul 2026 16:12:57 +0000

Cursor may make up the difference. A ton of companies use Cursor and Cursor's UI and billing model pushes their in-house "Composer 2.5" model pretty heavily - which is a modded Kimi K2.5 model under the hood. Anyone using Cursor is likely using Chinese models at least some of the time.

New comment by speu in "DeepSeek 4 Flash local inference engine for Metal"

speu — Thu, 07 May 2026 16:42:44 +0000

I've been trying deepseek-v4-flash in OpenCode (via OpenRouter) and I'm blown away. It's no Opus, obviously, but it had zero issues with any regular coding task I threw at it. v4-flash is remarkably "good enough" for what I needed. The whole evening of coding cost me $0.52 in API credits.

New comment by speu in "DeepSeek V4 Pro at 75% off until 31 May"

speu — Thu, 07 May 2026 16:25:55 +0000

I've been using OpenCode for a few days now, I like it. It doesn't feel any "less heavy" than Claude Code (they're both massive piles of vibe-coded typescript) but for me it's essentially a 1:1 replacement for Claude Code.

Sidenote, I've been trying deepseek-v4-flash and I'm blown away. It's no Opus, but it's as cheap as tap water and punches far above its weight as a Flash model. I keep throwing tasks at it out of curiosity and it keeps solving them.