FOUNDER OF https://nitter.cf/t.co/ahVYWrq9QC https://nitter.cf/t.co/NzlbsW0usO
IN X
Joined April 2014
- Tweets29.3K
- Following1.5K
- Followers2.7K
- Likes78.3K
A single compromised laptop just wiped out $6.3 billion in 20 minutes.
Crypto spent a decade hardening onchain cryptography only to leave hot wallet withdrawal pipelines tied to standard employee endpoints.
Mathematical security is useless if a hijacked local session can authorize billions in treasury drain without physical quorum.
Are you enforcing hardware-isolated quorums, or still trusting developer laptops?
Kill AI boilerplate in Cursor with path-scoped rules:
1. Create `.cursor/rules/api.mdc`
2. Set frontmatter: `globs: "src/api/**"`
3. Add prompt rules: "Enforce Pydantic v2, explicit status codes, zero raw dicts"
4. Edit routes via Cmd+K or Composer
The agent loads constraints only when touching matching paths, slashing token bloat and dirty diffs.
You can cut your coding agent bills in half without sacrificing frontier reasoning.
Copilot Fusion benchmarks at $5.59 per task versus $11.42 for pure Claude Code Opus 5.5, trailing by only 2 points while consuming 7.2M tokens instead of 14M+.
I would swap out single-model agent pipelines for dynamic model orchestration today.
Are you running multi-model routers in production yet?
"AI code is buggy, I'd have to check every line."
No. Make Claude write the failing test first, then the code, then add a hook that runs tests every time it stops.
You check the tests, not every line. Whole loop below:
nitter.cf/Decoded08/status/21157…
Your AI agent can now go shopping. With a wallet.
MoonPay's PayBox just plugged Whop's stores into Claude, ChatGPT and Grok. Sellers change nothing.
The hard part was never search. It's who signs.
Would you let an agent buy without asking you first? Yes or no.
ALT Card: Your agent can now check out. Six steps of how MoonPay PayBox lets an AI agent search Whop stores, prepare an order, show the total and recipient, and pay only after passkey approval or within preset limits.
Token prices fell 98%, but your AI agent bill just tripled.
A simple task cost $0.04 in 2023. Run it through an agentic loop with tool calls and retries today, and it hits $1.20.
Lower per-token pricing is irrelevant when multi-step reasoning creates a 30x volume multiplier.
Are you capping spend per completed task, or still budgeting by seat?
Triple your coding throughput with isolated Claude Code sessions:
1. Isolate the git worktree: `claude --worktree branch-name`
2. Scope changes before writing code: `/plan`
3. Query docs without adding history: `/btw <question>`
4. Prune token bloat before verifying: `/compact`
Zero context bleed between parallel tasks and clean PRs every time.
BOOKMARK THIS:
6 open-source AI agent repos launched in the last 2 weeks that turn your coding agent into a whole new tool.
Each already has 400+ GitHub stars (checked tonight) 🧵
ALT GitHub page of enesozturk/dimensional-drawing showing an Apple-style technical drawing of a UI card
ALT GitHub page of daveebbelaar/bama, Build Any Mac App agent skills
ALT GitHub page of alchaincyf/huashu-motion, launch films by your coding agent
Your AI prototyping bill just dropped by up to $500 a month.
OpenAI now lets eligible ChatGPT Pro and Business subscribers claim up to $500/month in API credits by linking their API org.
I would route all agent evals and staging loops here before touching primary cloud budgets.
Are you claiming subscription credits for development, or keeping API billing isolated?
Most Claude Code users never press Shift+Tab twice.
That's plan mode. Claude researches and writes the plan, you approve it, then it builds. It's the single habit that stops it from wrecking your codebase.
Full command list here:
nitter.cf/Decoded08/status/21157…
