The Changelog   /     Programming with LLMs (Interview)

Description

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!

Subtitle
Duration
1:31:22
Publishing date
2025-02-19 19:00
Link
https://changelog.com/podcast/629
Contributors
Enclosures
https://op3.dev/e/https://cdn.changelog.com/uploads/podcast/629/the-changelog-629.mp3
audio/mpeg

Shownotes

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!

Join the discussion

Changelog++ members get a bonus 11 minutes at the end of this episode and zero ads. Join today!

Sponsors:

  • RetoolThe 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:

Show Notes:

Something missing or broken? PRs welcome!

Deeplinks to Chapters

0 This week on The Changelog
255
1158 More on Adam's Tailscale AI
255
1526 Sponsor: Augment Code
255
1735 David's LLM journey
255
2211 Reasoning models
255
227 Start the show!
255
2289 Code completion
255
2353 The right model for the job
255
2405 The running shoe analogy
255
2568 Putting the shoes on
255
2616 Early days
255
2795 Building non-chat things
255
2951 Sketch.dev granularity
255
306 No Tailscale AI
255
3338 How Sketch works with LLMs
255
3628 Let it ask
255
3820 Sponsor: Temporal
255
3943 Well-suited programming languages
255
4171 Swapping out Go
255
4295 LLM Engine Optimization
255
4604 LLM ads coming soon
255
4807 Getting started advice
255
491 !Exciting proposals
255
4975 Any good guides?
255
5062 Massaging your AI
255
5100 Being nice to your AI?
255
520 Not a sponsor!
255
5357 Closing thoughts and stuff
255
61 Sponsor: Retool
255
615 Tailscale's free plan
255
668 Boring software
255
795 Adam's Tailscale AI
255
973 How many models should there be?
255