Arindam Majumder 𝕏
@Arindam_1729 • 9,253 subscribers
a builder. founder @studio1hq youtube: https://t.co/ZE1x8oT6Ac
Shorts
Videos
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.
Arindam Majumder 𝕏13,664 次观看 • 6 天前
Just tested Kimi.ai K3 against GPT-5.6 and Grok 4.5 on the same task: build a Subway Surfers game. Kimi K3 was my favorite. Better UI, smoother gameplay, and the overall experience felt more polished. GPT-5.6 was solid too, while Grok 4.5 fell behind on the UI. The interesting part is that all three needed at least one follow-up prompt. Kimi also took a bit longer to generate, but the extra time paid off. Ran Kimi K3 through Nebius Token Factory. Low inference cost + a really capable open source model is a great combo.
Arindam Majumder 𝕏46,107 次观看 • 2 个月前
The MCP finally has proper authentication! It now supports OAuth 2.1 out of the box. That means proper authentication for AI agents and MCP tools is finally standardized. No more hacked-together API keys or custom token logic. With OAuth 2.1 + MCP, you can now: - Dynamically register clients - Issue & verify scoped JWT tokens - Track which agent acted for which user - Plug into existing IdPs (Auth0, Clerk, Firebase, etc.) I’ve been testing it with Scalekit, a lightweight OAuth layer built for MCP servers. It adds full discovery, token flow, and audit logs with minimal config. This is the missing piece for secure, multi-agent systems. Auth that actually works.
Arindam Majumder 𝕏11,525 次观看 • 1 年前
没有更多内容可加载