hn.today

DeepSeek v4.1 flash on OpenCode pretty good

github.com7 points0 comments

SHEV is a minimal decision-maker that consumes one whole message (an email, ticket, review, etc.) and returns a single, structured JSON decision containing an actionable string, a boolean take_action, a numeric confidence, and a generated_response. It deliberately avoids agents, orchestration, long prompt engineering, or line-by-line parsing: one message in, one judgment out. The interface supports either a small local ternary model (Bonsai) running on Apple Silicon via MLX or a remote DeepSeek backend via API key; the local default is Bonsai, while DeepSeek runs over the network and stores its key in ~/.config/shev/config.json. Decisions are appended to responses.json so other tools can read the records.

Installation offers a one-line curl installer, an npm package (@noorslvt/shev) with caveats about registry names and install scripts, or cargo install from the repo; uninstall cleans binaries, keys, local models, and tracked chat records. The terminal UI shows model output and the raw JSON for the current decision side-by-side, with commands for loading files, managing models/keys, copying JSON, history, MCP bridge/tools, and quick keybindings (enter to send, ctrl+t to switch model). Recommended hardware is Apple Silicon (M1 or newer, 16 GB ideal), though DeepSeek lets it run on any Rust-supported platform.

Read on github.com0 comments on Hacker News

Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.

More in Other

Super Intelligence

Super Intelligence

The U.S. government is leading efforts to develop super intelligence (SI) technology through initiatives like the Genesis Mission and SI education programs. These efforts aim to establish American dominance in SI for economic, security, and scientific advancement. (si.gov)

The daily digest

Today's best Hacker News stories, summarized and screenshotted, one email a day.