Shane Crawford

[Shane Crawford @ShaneCrawfnmj0]

https://t.co/KJSRJ9qltP

[Shane Crawford @ShaneCrawfnmj0]

#minichat #teenageee (bioo)

[Shane Crawford @ShaneCrawfnmj0]

#minichat #teenageee (bioo)

[Shane Crawford @ShaneCrawfnmj0]

big if true

[Nayib Bukele @nayibbukele]

Even with crime rates already at razor thin levels, we’re still driving them even lower.

On track to become the safest country in the world.

[Elon Musk @elonmusk]

The new Tesla Roadster is a candidate for greatest product demo of all time

[Arindam Majumder 𝕏 @Arindam_1729]

Your coding agent is wasting expensive tokens on decisions a tiny model can make in milliseconds.

Jev + Claude Code is a pretty clever fix.

Think of Jev as the fast gut brain. It handles simple yes/no decisions, classification, and scoring.

Claude is the slow thinking brain. It only steps in when the task needs real reasoning.

here’s how to wire them together:

1. Give Claude Code Jev tools

/plugin marketplace add rashedInt32/jev-mcp

/plugin install jev@jev-mcp

Claude can now use Jev for classify, score, and check.

2. Find the right code without reading everything

npm install -g @dzhng/jev

jevgrep "how are payments retried?" ./my-project

Ask a question about your codebase and get the relevant files back.

The author measured ~30% lower costs on the same tasks.

3. Let your agent delegate automatically

npx skills add altryne/jevify --skill jevify

This teaches your agent to hand repetitive yes/no decisions to Jev instead of burning tokens on Claude.

4. Cut wasted context

fast-jev-compaction replaces Claude Code's usual summary with Jev-based decisions, removing stale tool calls while preserving everything else word for word.

the idea is simple:

stop paying for deep reasoning when a fast, cheap decision is enough.

less wasted inference. lower costs. faster agent runs.

save this for your next Claude Code session.

[Peter Kostis @peterjkostis]

It takes time to read and comprehend this. But if you do, you will realize the immense potential of NWBO and the DCVax franchise.... but more importantly the hope for future cancer patients.

[Shane Crawford @ShaneCrawfnmj0]

Si tu pitch necesita 15 minutos solo para explicar el problema, empiezo a sospechar que el problema no existe. @grok what makes this work? 🔥