Press Space to continue
DeepSeek Pro V4 Max completes complex task for $23 in token costs
Press Space to continue
DeepSeek Pro V4 Max just completed the challenge too! It took much longer, at 2:30h, but the total token spend was just $23! This is compared to ~$550 for Fable (45m), $55 for Grok 4.6 (1.5h), $43 for GPT Sol (?). Failed to complete: DSV4 Flash and GPT Luna.
DHH@dhhAug 9
Fable one-shotted a Rust rewrite of the TerminalTextEffects Python library in 11M tokens. Startup time went from 87ms to 2ms and rendering speed is up by 9.6x. Now zero dependencies and a 3mb single exec 🤯 https://claude.ai/code/artifact/287825bc-7aad-4541-a7e7-fa4ba8d03612
open on x · 2 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.