Ali Pullen

person on 1 show · 5 statements across 1 episodes · said 4 times in 1 episodes since 2024

Latent Space 4

Mentions by year, every show

tap a year for its mentions
0021412024episodesmentions
0112024episodes it came up in
0020.5412024episodesmentions per episode

Latent Space 4

2024 4 mentions in 1 episode

every mention on every show, scene by scene, with the transcript →

5 statements about Ali Pullen, every show

LATENT SPACE Assertion Supported
Cosine's Genie achieved roughly 66% codebase retrieval accuracy across benchmark tasks
“And I think in our technical report, I can't remember the exact number, but I think it was around 65 or 66% retrieval accuracy overall measured on. We know what lines we need for these tasks to find for the task to actually be able to be completed. And we foun…”
Alistair Pullen Aug 22, 2024 ▶ 27:31 Is finetuning GPT4o worth it?
Generating hypothetical code from queries significantly improves codebase retrieval accuracy
“So what we ended up, the first approach we took and that kind of did well enough for a long time was, okay, let's train a model to be able to take in English code queries and then produce a hypothetical Code snippet that might look like the answer, embed that,…”
Alistair Pullen Aug 22, 2024 ▶ 24:55 Is finetuning GPT4o worth it?
Standard semantic embedding similarity fails on codebase retrieval tasks
“And once you've done that, I will write a query saying like, find me some authentication code or something, embed it, and then do the cosine similarity and get the top of K right. That doesn't work. And I wish it did work. Don't get me wrong. It doesn't work w…”
Alistair Pullen Aug 22, 2024 ▶ 24:32 Is finetuning GPT4o worth it?
LATENT SPACE Assertion Not checkable as stated
Pullen: Enterprise customers are growing more willing to share proprietary codebases
“Mostly we've actually seen, I'd say people becoming more amenable to the idea over time, actually rather than more skeptical, because I think they can see the upside.”
Alistair Pullen Aug 22, 2024 ▶ 20:43 Is finetuning GPT4o worth it?
LATENT SPACE Assertion Contradicted
Pullen: Most scraped open-source data consists of README and documentation updates
“When you scrape enough of it, most of open source is updating readmes and docs.”
Alistair Pullen Aug 22, 2024 ▶ 19:17 Is finetuning GPT4o worth it?

← every entity, every show

Made with StarZero

Turn any episode into a week of clips.

This entire site, thousands of episodes across every show transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.