In growing the content material for our Could 8 digital convention Coding with AI: The Finish of Software program Growth as We Know It, we couldn’t assist however need to characteristic Harper Reed, whose latest put up “My LLM Codegen Workflow ATM” so completely encapsulates the form of experimentation that builders are going by as they arrive to grips with the transformation that AI is bringing to how they work, what they’ll accomplish, and which instruments they need to be adopting. Harper lays out his present workflows and instruments with detailed examples for each greenfield code and legacy code that make it straightforward for others to be taught from what he’s performed. It’s an incredible mannequin for the form of data sharing we hope to engender with the upcoming occasion and others that can observe. When you haven’t learn it but, go accomplish that now.
In an e-mail to me, my previous pal Nat Torkington had this to say about Harper’s put up:
Be taught quicker. Dig deeper. See farther.
I really feel like there are ascending ranges of nerd on this:
– immediate hacks
– instruments to combine into your workflow
– context hacks (e.g., construct a necessities doc with the LLM, then get it to code to these necessities)
– use of particular fashions/options (e.g., reasoning vs. non-reasoning LLMs)
– {custom} workflows/instruments assembled from items, however which actually are custom-built to that particular person’s workflow
ALL of those are issues that we need to cowl in our upcoming occasion. So I’d like to make use of Harper’s piece as a immediate and context hack to all of you, to make clear what we’re searching for on the occasion. Coding with AI will characteristic fireplace chats with people like Jay Parikh, Addy Osmani and Gergely Orosz, Chip Huyen, and Shawn @swyx Wang, and talks by Harper, Simon Willison, Chelsea Troy, Steve Yegge, Andrew Stellman, and others. However we’re nonetheless searching for extra experiences from the trenches, introduced as five-minute lightning talks (a format Nat Torkington initially developed for our Perl Convention almost 30 years in the past, and that was a beloved characteristic of all our conferences thereafter).
Classes we’re inquisitive about embody “my favourite AI device,” “my favourite AI immediate or context hack,” “my workflow,” “my challenge that I’d by no means have thought to attempt with out the convenience of experiment I get with AI,” and so forth. Along with the lightning talks at this occasion, we’re additionally planning a future recurring occasion that’s fully dedicated to a reside model of the form of full show-and-tell that Harper did so nicely.
So, go learn Harper, and present us what you’ve received! Ideally, you’ll not solely give us the complete model but in addition distill explicit, usable classes from it. Right here’s some extra knowledge from Nat’s e-mail to get you began:
The extra the mechasuit is designed to your cortex, the much less transferable it’s to different folks. The danger is you begin with “listed below are six instruments I exploit in my very own advanced workflow in a language you don’t recognise to unravel issues you don’t have” and lose folks in a flood of random device names.
[We want to be] in a position to take a look at completely different folks’s “I code with AI!” workflows and break them down [as Harper does] so [our viewers] can go “nicely, that’s cool however I’m not utilizing vi and command-line instruments don’t play nicely with Visible Studio, so I’ll simply steal your context hacks for working with large code bases in Copilot.”
Addy Osmani added to our e-mail dialog:
Constructing on the “ascending ranges of nerd” framework (which I really like!), we might construction a few of the “how I work” content material to particularly handle completely different developer expertise ranges. For instance:
- Junior devs: give attention to constructing that important analysis mindset and understanding when/the best way to successfully use AI instruments
- Mid-level: exploring workflow integration and context optimization
- Senior: deep dives into {custom} tooling and superior immediate engineering
Submit your proposals (together with, ideally, a put up modeled on Harper’s that we will publish right here on the O’Reilly Radar weblog) on the current name for displays hyperlink. We’ve up to date the submission deadline to March 12 and the occasion date from April 24 to Could 8 to present you a bit extra time to do your reasoning after which reply to this revised immediate.
On Could 8, O’Reilly Media will probably be internet hosting Coding with AI: The Finish of Software program Growth as We Know It—a reside digital tech convention spotlighting how AI is already supercharging builders, boosting productiveness, and offering actual worth to their organizations. When you’re within the trenches constructing tomorrow’s improvement practices immediately and inquisitive about talking on the occasion, we’d love to listen to from you by March 12. You could find extra data and our name for displays right here.
