---
title: "Slides: Benchmarking semantic code retrieval on Claude Code — Kuba Rogut, Turbopuffer"
category: "slides"
video_id: "zKk7sDMGDEQ"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Benchmarking semantic code retrieval on Claude Code — Kuba Rogut, Turbopuffer

## Source Video
[Benchmarking semantic code retrieval on Claude Code — Kuba Rogut, Turbopuffer](https://www.youtube.com/watch?v=zKk7sDMGDEQ)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/zKk7sDMGDEQ/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/zKk7sDMGDEQ/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.93`
- Text source: advanced OCR `rapidocr-live/border-trim/contrast`.
- OCR decision: ready — dense screenshot-style slide with small text and mixed elements

Slide text:

> claude doesn't use semantic code search turbopuffer
> Ethan Lipnik @EthanLipnik · Jan 30
> Does anyone know why Codex and Claude doesn't use cloud-based
> embeddings like Cursor to quickly search through the codebase?
> AIE 68 18 658 ll 266K 口
> @bcherny Boris Cherny
> Early versions of Claude Code used RAG + a local vector db, but we
> found pretty quickly that agentic search generally works better. It is also
> simpler and doesn't have the same issues around security, privacy,
> staleness, and reliability.
> 9:56 PM · Jan 31, 2026 · 1.1M Views
> Engineering the future of Al


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/zKk7sDMGDEQ/slide-001.jpg) — `speaker_stage` confidence `0.2`; speaker at podium; projected title slide is background, not a readable presentation frame

Classification audit: `raw/sources/slide-ai-classification/slides/zKk7sDMGDEQ/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.