# Agents make software deprecations harder

Markdown copy of https://realalpha.app/s/agents-make-software-deprecations-harder/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Erik Bernhardsson](https://realalpha.app/builders/erik-bernhardsson/) · Erik Bernhardsson is co-founder and CEO of Modal. · Co-founded Modal, the high-performance cloud for AI teams; previously led Spotify's music recommendation and data infrastructure teams.
- Host: [Jacob Effron](https://realalpha.app/people/jacob-effron/) · AI Investor, Redpoint Ventures · Growth investor in Abridge, Ramp and Physical Intelligence; ex-Flatiron Health.
- Host: Pat Chase · AI Investor, Redpoint Ventures
- Show: Unsupervised Learning
- Episode: [Modal CEO on the Future of Inference, the Chaos of the GPU Market & Origins of the Sandbox Bet](https://realalpha.app/v/HJDekXH-h5c/), Oct 28, 2026
- Moment: 30:17 to 33:21 of the episode (3 min), playing on https://realalpha.app/s/agents-make-software-deprecations-harder/; the episode from there: https://realalpha.app/v/HJDekXH-h5c/?t=1817

## Quote

> “we can't just rely on like you know remove it from the documentation and wait three months because like **it's in the training data**”
> — [Erik Bernhardsson](https://realalpha.app/builders/erik-bernhardsson/) at [31:26](https://realalpha.app/v/HJDekXH-h5c/?t=1886) · Unsupervised Learning

## Takeaways

1. Old code in training data can keep deprecated APIs in use.
2. Modal tests whether generated code builds and runs.
3. Agent recommendations can create a software distribution flywheel.

## About this segment

Agents trained on old code keep using deprecated APIs, so Modal has lengthened some deprecation windows and tests agent-generated code. It also tracks whether agents recommend Modal.

From “Modal CEO on the Future of Inference, the Chaos of the GPU Market & Origins of the Sandbox Bet”, Oct 28, 2026. [Watch the full episode](https://realalpha.app/v/HJDekXH-h5c/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[30:19](https://realalpha.app/v/HJDekXH-h5c/?t=1819) I mean, it's interesting to think about kind of the, you know, how different the world is with these really powerful coding agents. And obviously, I think, you know, part of what I believe your co-founders talked about is kind of the shift even in who the consumer of modal is over time, right, from a developer to, you know, to agents themselves, right? And I'm curious, like, how you think about what that means for modal as a business and some of the decisions you might make differently as, you know, more and more of folks interacting with modal are either doing it via an agent or purely end-to-end an agent.

[30:48](https://realalpha.app/v/HJDekXH-h5c/?t=1848) it's actually changed like a lot less than you than i think i would have expected uh it turns out agents i mean like in the early days like we built modal in order to give engineers a better developer experience and the ability to move faster it turns out like agents kind of want the same thing like they want fast feedback loop they want like good error messages good documentation a lot of the stuff like that that engineers want to so so most of the stuff is actually quite similar i do think it's like certain things a little bit harder like one of the things like we found for instance like deprecations is much more annoying because uh agents are trained often on like a lot of old code that exists online so removing features is much harder for us like we can't just rely on like you know remove it from the documentation and wait three months because

[31:33](https://realalpha.app/v/HJDekXH-h5c/?t=1893) like it's in the training data people will use you know lms to generate modal code and that will be like you know using deprecated features uh and that's like quite hard to change so we've had to change our deprecation window for quite a lot. Another thing we've started doing quite a lot is also setting up a lot of automated pipelines to basically have like LMs continuously write modal code and making sure it compiles and or not compiles.

[32:00](https://realalpha.app/v/HJDekXH-h5c/?t=1920) but it builds and runs, trying to just catch things that agents struggle with. And then maybe another thing we spend a lot of time on is more like agent optimization stuff, which is actually more similar to search engine optimization. If you can go and ask Cloud Code something like, hey, I want to do something with inference. I want to deploy this model and not say anything about modal and just see which tool does it recommend.

[32:27](https://realalpha.app/v/HJDekXH-h5c/?t=1947) And that obviously is something we wanted to recommend. model as much as possible so that's something we track internally make sure that you know over time like and actually i think that's like something that that um will change software engineering a little bit maybe almost like to do worse like i like i feel like in a way like because of the training data and and the training loops like there's more like you know like incumbency power in a way like there's more staying power in software today like if you get inside the training data and you get the models to recommend, you know, a certain framework. I've heard people say like, oh, I'm just going to use React for everything because agents are really good at it.

[33:04](https://realalpha.app/v/HJDekXH-h5c/?t=1984) I'm not going to try these like new fancy front end frameworks, right? Like, I think there's like something similar with like a lot of the frameworks today is like that staying power is actually very, very valuable now. So we obviously want to make sure that agents recommend modal as much as possible because that creates like a little bit of a flywheel. And one thing I'm struck by is you