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
29 articles name Thariq Shihipar, excluding author credits.
Page 1 of 3
- Karpathy: Stop Reading LLM Output as Plain Text — Ask for a Video Instead →
On October 2, 2026, Andrej Karpathy posted a short ladder for understanding what language models write: controlled-language text, then diagrams, then HTML pages, then bespoke explainer videos. Here is what each rung means, the exact prompts to try, and where the advice breaks down.
- claude.dev Is Anthropic's Developer Hub — Not a New Model →
On October 1, 2026 ClaudeDevs said claude.dev is the new home for people building with Claude. The site already held months of team writing. This is a map of what belongs there versus docs.claude.com, plus the terminal easter eggs that are not Claude Code commands.
- Thariq's Case Against Shipping 10x More Features Just Because Models Got Smarter →
"The right way to use model capabilities is not to ship 10x more features to prod" — Anthropic's Thariq Shihipar made a direct case against feature-velocity as the point of better models, arguing the actual leverage is in spending saved time on understanding users and prototyping, not output volume. The replies split between agreement and a pointed question: does this survive contact with a business that just wants more shipped?
- The "Interview Me" Prompt That Fills Claude's Memory in One Session →
On September 11, 2026, Anthropic's Thariq Shihipar shared a prompt that tells Claude to interview you in depth — using free text or the AskUserQuestion tool — and save what it learns to memory. Blake Robbins' quoted post framing sparked 232K views. explainx.ai breaks down the prompt, the staleness problem it doesn't solve, and how it compares to CLAUDE.md.
- NEAR AI Reportedly Solved Putnam Bench for $111 — 250x Cheaper →
According to reporting circulating on September 6-7, 2026, NEAR AI ran Putnam Bench — a benchmark built from Putnam Mathematical Competition problems — for roughly $111 in total inference cost, described as a 250x reduction versus the second-cheapest prior result. We could not locate a primary source confirming the exact score, pass threshold, or methodology, so this is a reported claim, not a verified one — but the cost-efficiency angle is worth taking seriously either way.