Engineer working on Claude Code at Anthropic
Thariq Shihipar
Thariq Shihipar is an engineer working on Claude Code at Anthropic. His projects span AI agents, developer tools, gaming, and academic publishing.
About Thariq Shihipar
Thariq Shihipar is an engineer and entrepreneur working on Claude Code at Anthropic, according to his official website. His published technical writing covers subjects including language-model-based sorting and AI interpretability.
Shihipar previously founded the gaming company One More Multiverse and co-founded PubPub, an academic publishing platform. His projects also include tools for creating AI agents, AI-assisted copyediting, and email prioritization. He studied at the MIT Media Lab.
Mentioned in our coverage
25 articles name Thariq Shihipar, excluding author credits.
Page 2 of 3
- Recursive Model Improvement — Lee Robinson's AI Engineer Talk (Cursor, SpaceXAI) →
Cursor ML lead Lee Robinson's AI Engineer stage talk is now live — recursive model improvement via outer feedback loops and inner RL evals, SpaceX Colossus compute, textual feedback for credit assignment, and agents that train models from Slack. explainx.ai recaps the full transcript and X reaction.
- Claude Code Artifacts + MCP: Live Dashboards With Viewer-Scoped Auth →
Anthropic's ClaudeDevs account announced artifact MCP connectors: build a dashboard once, and each viewer pulls live data through their own connectors. explainx.ai explains viewer-scoped auth, plan limits, admin toggles, and how this extends Thariq's thick-artifacts framework.
- DoorDash dd-cli: Order Food From Your AI Agent in the Terminal →
DoorDash opened a limited beta for dd-cli, a command-line interface that lets AI agents search restaurants, find deals, and complete real payments from the terminal. explainx.ai maps the apps-for-agents thesis, macOS-only waitlist constraints, Paul Graham memes vs skepticism, and checkout safety next to today's Codex $HOME news.
- Thin Prompts, Thick Artifacts, Thin Skills: Thariq’s Claude Code Framework →
Thariq Shihipar on the Claude Code team distilled his prompting framework in one tweet: thin prompts, thick artifacts + context, thin skills. With ~82K views and a Garry Tan reply in the thread, here is what each layer means, when skills should stay small, and copy-paste examples you can use today.
- Claude Fable 5 Solves 6-Month String Theory Standstill — Yuji Tachikawa SymPy Case →
HN/HuggingNews Jul 12: Kavli IPMU professor Yuji Tachikawa says Fable solved a stalled heterotic-string collaboration — SymPy checks included. @42_gravity and @pmarca amplified. explainx.ai separates signal from hype.