High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works

Public evidence record

Alistair Pullen

Published podcast speaker

Claims
15
Episodes
1
Shows
1
Named items
0

Claim ledger

What Alistair said.

15 transcript-backed records

01 / evaluation

So we could see if we were, you know, actually helping ourselves or not. And initially, one of the biggest performance gains that we saw when we were work, when we did work on the RAG a bit was giving it the ability to use the LSP to like go to definition and really try to get it to emulate how we do that, because I'm sure when you go into an editor with that, where like the LSP is not working or whatever, you suddenly feel really like disarmed and naked.

“So we could see if we were, you know, actually helping ourselves or not. And initially, one of the biggest performance gains that we saw when we were work, when we did work on the RAG a bit was giving it the ability to use the LSP to like go to definition and really try to get it to emulate how we do that, because I'm sure when you go into an editor with that, where like the LSP is not working or whatever, you suddenly feel really like disarmed and naked.”
Speaker
Alistair Pullen
Publisher
Latent Space

03 / evaluation

It's hilarious, like we had to filter out so much of that stuff because when we first did the 16k model, like the amount of readme updating that went in, we did like no data cleaning, no real, like, we just sort of threw it in and saw what happened. And it was just like, It was really good at updating readme, it was really good at writing some comments, really good at, um, complaining in Git reviews, in PR reviews, rather, and it would, again, like, we didn't clean the data, so you'd, like, give it some feedback, and it would just, like, reply, and, like, it would just be quite insubordinate when it was getting back to you, like, no, I don't think you're right, and it would just sort of argue with you, so The process of doing all that was super interesting because we realized from the beginning, okay, there's a huge amount of work that needs to go into like cleaning this, getting it aligned with what we want the model to do to be able to get the model to be useful in some way.

“It's hilarious, like we had to filter out so much of that stuff because when we first did the 16k model, like the amount of readme updating that went in, we did like no data cleaning, no real, like, we just sort of threw it in and saw what happened. And it was just like, It was really good at updating readme, it was really good at writing some comments, really good at, um, complaining in Git reviews, in PR reviews, rather, and it would, again, like, we didn't clean the data, so you'd, like, give it some feedback, and it would just, like, reply, and, like, it would just be quite insubordinate when it was getting back to you, like, no, I don't think you're right, and it would just sort of argue with you, so The process of doing all that was super interesting because we realized from the beginning, okay, there's a huge amount of work that needs to go into like cleaning this, getting it aligned with what we want the model to do to be able to get the model to be useful in some way.”
Speaker
Alistair Pullen
Publisher
Latent Space

04 / commitment

When we have more resource as a company, and, More time and, you know, once all the craziness that has just happened sort of dies down a bit, we are going to, you know, work on that mix.

“When we have more resource as a company, and, More time and, you know, once all the craziness that has just happened sort of dies down a bit, we are going to, you know, work on that mix.”
Speaker
Alistair Pullen
Publisher
Latent Space

06 / belief

Honestly, people who are just willing to try something new, like the Genie UX is, is different to a conventional IDE, give it a chance, like that what we really do believe in this whole idea of like developers work is going to be abstracted, you know, levels higher than just the code, we still let you touch the code, we still want you to dive into the code if you need to, but Fundamentally, we think that if you're trying to offload the coding to a model, the model should do the coding and you should be in charge of guiding the model.

“Honestly, people who are just willing to try something new, like the Genie UX is, is different to a conventional IDE, give it a chance, like that what we really do believe in this whole idea of like developers work is going to be abstracted, you know, levels higher than just the code, we still let you touch the code, we still want you to dive into the code if you need to, but Fundamentally, we think that if you're trying to offload the coding to a model, the model should do the coding and you should be in charge of guiding the model.”
Speaker
Alistair Pullen
Publisher
Latent Space

07 / preference

improved reasoning data and just like I can keep bootstrapping and keep leapfrogging every single time. And that is like super exciting to me because I don't, I welcome like new models so much because immediately it just floats me up without having to do much work, which is always nice.

“improved reasoning data and just like I can keep bootstrapping and keep leapfrogging every single time. And that is like super exciting to me because I don't, I welcome like new models so much because immediately it just floats me up without having to do much work, which is always nice.”
Speaker
Alistair Pullen
Publisher
Latent Space

08 / preference

I think obviously the most important tools to these agents are like being able to retrieve code from a code base, being able to read Stack Overflow articles and what have you and just be able to essentially be able to Google like we do is definitely super useful.

“I think obviously the most important tools to these agents are like being able to retrieve code from a code base, being able to read Stack Overflow articles and what have you and just be able to essentially be able to Google like we do is definitely super useful.”
Speaker
Alistair Pullen
Publisher
Latent Space

10 / prediction

Um, and of course, like, companies building in this space, we're all going to end up, you know, complying with the same rules, and there are going to be new rules that come out to make sure that we're looking at your code, that everything is safe, and so on. So from what we've seen so far, we've spoken to some very large companies that you've definitely heard of and all of them obviously have stipulations and many of them want it to be sandbox to start with and all the like very obvious things that I, you know, I would say as well, but they're all super keen to have a go and see because like, despite all those things, if we can genuinely Make them go faster, allow them to build more in a given time period and stuff.

“Um, and of course, like, companies building in this space, we're all going to end up, you know, complying with the same rules, and there are going to be new rules that come out to make sure that we're looking at your code, that everything is safe, and so on. So from what we've seen so far, we've spoken to some very large companies that you've definitely heard of and all of them obviously have stipulations and many of them want it to be sandbox to start with and all the like very obvious things that I, you know, I would say as well, but they're all super keen to have a go and see because like, despite all those things, if we can genuinely Make them go faster, allow them to build more in a given time period and stuff.”
Speaker
Alistair Pullen
Publisher
Latent Space

11 / evaluation

Like, we are right on the edge, and like, we are working, genuinely working with them in figuring out how stuff works, what works, what doesn't work, because no one's doing No one else is doing what we're doing.

“Like, we are right on the edge, and like, we are working, genuinely working with them in figuring out how stuff works, what works, what doesn't work, because no one's doing No one else is doing what we're doing.”
Speaker
Alistair Pullen
Publisher
Latent Space

12 / preference

I like our approach because we can be super agile and be like, Oh, well, Anthropic have just released whatever, uh, you know, and it might have half a million tokens and it might be really smart.

“I like our approach because we can be super agile and be like, Oh, well, Anthropic have just released whatever, uh, you know, and it might have half a million tokens and it might be really smart.”
Speaker
Alistair Pullen
Publisher
Latent Space

13 / evaluation

As soon as we did that, because in the entire run up to that we built the data pipeline, we already had all that set up, so we were like, right, we have the data, now we have the model, let's put it through and iterate, essentially, and that's, that's where, like, Genie as we know it today, really was born.

“As soon as we did that, because in the entire run up to that we built the data pipeline, we already had all that set up, so we were like, right, we have the data, now we have the model, let's put it through and iterate, essentially, and that's, that's where, like, Genie as we know it today, really was born.”
Speaker
Alistair Pullen
Publisher
Latent Space

14 / evaluation

You have no idea why or how, for the most part, unless there are some comments, which, you know, anyone who's worked in a company realizes PR reviews can be a bit dodgy at times, but you see that you lose so much information at the end, and that's perfectly fine, because PRs aren't designed to be something that perfectly preserves everything that happened, but What we realized was if you want something that's a software engineer, and very crudely, we started with like something that can do PRs for you, essentially, you need to be able to figure out why those things happened.

“You have no idea why or how, for the most part, unless there are some comments, which, you know, anyone who's worked in a company realizes PR reviews can be a bit dodgy at times, but you see that you lose so much information at the end, and that's perfectly fine, because PRs aren't designed to be something that perfectly preserves everything that happened, but What we realized was if you want something that's a software engineer, and very crudely, we started with like something that can do PRs for you, essentially, you need to be able to figure out why those things happened.”
Speaker
Alistair Pullen
Publisher
Latent Space

15 / commitment

Because, fundamentally, to build a product like this, you need to get as much information in front of the model as possible, and make sure that everything it ever writes in output can be read.

“Because, fundamentally, to build a product like this, you need to get as much information in front of the model as possible, and make sure that everything it ever writes in output can be read.”
Speaker
Alistair Pullen
Publisher
Latent Space
Search evidence