
The Changelog: Software Development, Open Source
Programming with LLMs (Interview)
Feb 19, 2025 · 1 hr 31 min · 87.9 MB
0:00-1:31:22
Streams straight from the publisher. PodNod never proxies or re-hosts episode audio.
For the past year, David Crawshaw has intentionally sought ways to use LLMs while programming, in order to learn about them. He now regularly use LLMs while working and considers their benefits a net-positive on his productivity. David wrote down his experience, which we found both practical and insightful. Hopefully you will too!
Changelog++ members get a bonus 11 minutes at the end of this episode and zero ads. Join today!
Sponsors:
- Retool – The low-code platform for developers to build internal tools — Some of the best teams out there trust Retool…Brex, Coinbase, Plaid, Doordash, LegalGenius, Amazon, Allbirds, Peloton, and so many more – the developers at these teams trust Retool as the platform to build their internal tools. Try it free at retool.com/changelog
- Augment Code – Developer AI that uses deep understanding of your large codebase and how you build software to deliver personalized code suggestions and insights. Augment provides relevant, contextualized code right in your IDE or Slack. It transforms scattered knowledge into code or answers, eliminating time spent searching docs or interrupting teammates.
- Temporal – Build invincible applications. Manage failures, network outages, flaky endpoints, long-running processes and more, ensuring your workflows never fail. Register for Replay in London, March 3-5 to break free from the status quo.
Featuring:
- David Crawshaw – Website, GitHub, Bluesky, X
- Adam Stacoviak – Website, GitHub, LinkedIn, Mastodon, X
- Jerod Santo – Website, GitHub, LinkedIn, Mastodon, X
Show Notes:
- How I program with LLMs
- sketch.dev
- merde.ai: ai-fixed merge conflicts
- How Tailscale’s free plan stays free
Something missing or broken? PRs welcome!
Join the discussion
changelog.zulipchat.comChangelog++
changelog.comRetool
retool.comAugment Code
augmentcode.comTemporal
temporal.ioReplay in London, March 3-5
replay.temporal.ioWebsite
crawshaw.ioGitHub
github.comBluesky
bsky.appX
x.comWebsite
adamstacoviak.comGitHub
github.comLinkedIn
linkedin.comMastodon
changelog.socialX
x.comWebsite
jerodsanto.netGitHub
github.comLinkedIn
linkedin.comMastodon
changelog.socialX
x.comHow I program with LLMs
crawshaw.iosketch.dev
sketch.devHow Tailscale’s free plan stays free
tailscale.comPRs welcome!
github.com
- 0:00This week on The Changelog
- 1:01Sponsor: Retool
- 3:47Start the show!
- 5:06No Tailscale AI
- 8:11!Exciting proposals
- 8:40Not a sponsor!
- 10:15Tailscale's free plan
- 11:08Boring software
- 13:15Adam's Tailscale AI
- 16:13How many models should there be?
- 19:18More on Adam's Tailscale AI
- 25:26Sponsor: Augment Code
- 28:55David's LLM journey
- 36:51Reasoning models
- 38:09Code completion
- 39:13The right model for the job
- 40:05The running shoe analogy
- 42:48Putting the shoes on
- 43:36Early days
- 46:35Building non-chat things
- 49:11Sketch.dev granularity
- 55:38How Sketch works with LLMs
- 1:00:28Let it ask
- 1:03:40Sponsor: Temporal
- 1:05:43Well-suited programming languages
- 1:09:31Swapping out Go
- 1:11:35LLM Engine Optimization
- 1:16:44LLM ads coming soon
- 1:20:07Getting started advice
- 1:22:55Any good guides?
- 1:24:22Massaging your AI
- 1:25:00Being nice to your AI?
- 1:29:17Closing thoughts and stuff