French-Owen: Claude Code and Codex Use Grep Rather Than Semantic Embeddings
Calvin French-Owen · We're All Addicted To Claude Code · Y Combinator · Feb 6, 2026 · at 11:16
Calvin French-Owen compares the context retrieval mechanisms of AI coding tools like Cursor, Claude Code, and Codex.
0:00 / 0:12exact quote · 12.6s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Like I think cursor takes an approach where they actually do semantic search, where they embed everything and figure out like, Hey, what query is closest to this? If you look at a codex or a cloud code they actually just use like grep.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Calvin French-Owen
French-Owen: The value of writing basic integration code has dropped to zero
“Segment is a funny business in that where we started was building these integrations, right? And so it's like, oh, you need to wire up, like, the same data going to, like, Mixpanel and Kissmetrics and Google Analytics, et cetera. And I think just writing that …”
French-Owen: Software developers will all become AI managers in the future
“I think in some sense, you're right that like everyone is going to become a manager in the future, or at least that's my hot take. But in order to get there are steps along the way and you have to really build a lot of trust in the model and understand what it…”
French-Owen: Claude Code Succeeds by Distancing Devs From Low-Level Code
“And I think it's important actually to quad code that it's not an IDE because it sort of distances you from the code that's being written. Like IDEs are all about exploring files, right? And you're like trying to keep all the state in your head and understand …”
French-Owen: LLMs enter the 'dumb zone' after exceeding context thresholds
“He has this concept of, like, the LLMs reaching the dumb zone, where it's like, after a certain amount of tokens It just starts, like, degrading in quality. And I actually think that's very true, especially if you think about, like, how the reinforcement learn…”
French-Owen: Codex Uses Periodic Compaction to Support Long-Running Tasks
“Where it will run compaction, like, periodically after each turn, and so Codex can continue to run for a very long time, and if you look at the percentage in the CLI, you'll see it, like, move up and down as compaction runs.”