AI Coding Assistants
topic on 11 shows · 22 statements across 19 episodes
the Y Combinator Startup Podcast 
More or Less 
Startups For the Rest of Us 
American Optimist 
Latent Space 
Lenny's Podcast 
No Priors 
the Startup Ideas Podcast 
the a16z Podcast 
Big Technology 
20VC
22 statements about AI Coding Assistants, every show
Top a16z Portfolio Engineers Now Write Over 90% of Code With AI
“Our most sophisticated engineers, you know, were doing whatever, 20% of their code, you know, with AI to like, you know, whatever, 90 plus.”
Human clarity is the bottleneck in AI software creation
“So I understood very early that coding is not the problem that we're solving for here, that the problem we're solving for is clarity, right?”
Andrew Ng: AI coding tools are more mature than 2016 image generators
“I think it's further along. I think in 2016 image generation wasn't super valuable.”
Andrew Ng: One engineer can now build six-month projects in a weekend
“There are so many projects that used to take, you know, six engineers, half a year to build, that today I or one of my engineers can build in the weekend.”
Sands: 65% to 70% of Stripe engineers use AI coding assistants daily
“65, 70% of engineers use them on the day to day.”
Labenz: Non-coders are performing legitimate frontier AI behavioral research
“Because you can get the AIs to code so well, I'm starting to see people who have never coded before. I'm working with one guy right now who's never coded before, but does have a sort of behavioral science background. And he's starting to do legitimate frontier…”
Agarwal: AI coding assistants will cause uninterpretable outages and endless firefighting
“And so it's pretty clear to us that, you know, and we were starting to use it ourselves and sometimes we didn't understand what the code was doing, but you know, we shipped it. And so it's like, well, if this is clearly, this is going to happen a lot more. And…”
Ramachandran: Capturing Editor Trajectories Lets AI Infer Intent Without Explicit Prompting
“If we actually understand that trajectory, then our ability for the AI to just be immediately be like, Oh, I understand your intent. This is what you want to do without you having to spell it all out for it. That is one like that kind of like magic would reall…”
Mohan: Explicit user prompting will soon become an anti-pattern in AI coding
“I actually think asking people to do things explicitly is probably going to be more of an anti-pattern if we can actually go and passively suggest the entire change for the user.”
Casado: AI Coding Assistants Only Double The Productivity Of 10x Software Engineers
“I think they make 10 X engineers two X.”
Martin Casado: Senior developers see higher relative productivity gains from AI
“So if you actually look at like relative productivity gains, it just turns out if you're a more senior developer, you will have better productivity gains and the, I mean.”
Ng: AI coding makes prototyping 10x faster, production only 50% faster
“When writing production quality code, maybe we're at 30 to 50% faster with AI systems. Hard to find a rigorous number. Maybe. Be as plausible to me. But in terms of building quick and dirty prototypes, we're not 50% faster. I think we're easily 10 times faster…”
Conrad: Large engineering organizations are not seeing headcount reductions from AI
“I, like, am very skeptical that AI will be employment conserving because I just think that, like, in basically every area, like, we have not seen, and I think most large engineering orgs have not seen, like, a huge number of efficiencies from these sort of, li…”
Bender: AI coding assistants accumulate undocumented technical debt
“As coding assessments, assistants, so that's sort of a machine translation problem between natural language and some programming language and there I really worry about technical debt where you have, you know, output code that was not written by a person that'…”
Mohan: Explicit user prompting will become an AI coding anti-pattern
“I actually think asking people to do things explicitly is probably going to be more of an anti-pattern if we can actually go and passively suggest the entire change for the user. So almost imagine as the user is using the product that we're going to suggest th…”
Sirota: System Interdependencies Prevent Fully Autonomous AI Software Engineering
“And I think at least the companies that we're working with, there are so many interdependencies when it comes to the systems that they're building. So in a very small subset of code, it can help and aid in how to, you know, finish a complete and end point. But…”
Podjarny: AI coding tools lower code quality by turning developers into reviewers
“I do think that it develops software of questionable quality in many places, because You're just kind of reviewing the codes that got generated as opposed to actually writing it, and so just naturally the amount of thought you put into it is, is, is far lesser…”
Brown: Describe current system behavior before instructing AI coding assistants
“Describe what's going on first, then tell it specifically what to do. You don't want to leave it up to chance.”
Brown: Inconsistent naming in codebases frequently trips up AI coding models
“Sometimes the naming can become an issue.
Not saying that's the issue now, but just kind of going through some common problems I've run into.”
Brown: Explicit runtime errors are preferable to blank screens for AI agents
“Error messages are good. Blank screens are bad, right? This is what should have popped up in the dev log, right? We should see the errors right here, and it actually knows what to do and we can actually just see how it reacts.”
Dave Morin says non-engineers cannot build software with plain English prompts
“For, like, the general person, you still can't just describe to people in English what you want and have it pop out the other side. Like, it's just, like, no chance. Nor will it even attempt to walk you through how to get to the other side.”