In growing the content material for our Might 8 digital convention Coding with AI: The Finish of Software program Improvement as We Know It, we couldn’t assist however wish to characteristic Harper Reed, whose latest submit “My LLM Codegen Workflow ATM” so completely encapsulates the form of experimentation that builders are going by way of as they arrive to grips with the transformation that AI is bringing to how they work, what they will 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 simple for others to be taught from what he’s performed. It’s an excellent mannequin for the form of info sharing we hope to engender with the upcoming occasion and others that can observe. Should you haven’t learn it but, go achieve this now.
In an e mail to me, my previous pal Nat Torkington had this to say about Harper’s submit:
Be taught sooner. 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 wish 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 hearth 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 studies 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 focused on embrace “my favourite AI instrument,” “my favourite AI immediate or context hack,” “my workflow,” “my mission that I’d by no means have thought to strive with out the benefit 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 totally dedicated to a stay model of the form of full show-and-tell that Harper did so properly.
So, go learn Harper, and present us what you’ve received! Ideally, you’ll not solely give us the total model but additionally 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 individuals. The chance is you begin with “listed here 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 individuals in a flood of random instrument names.
[We want to be] in a position to take a look at completely different individuals’s “I code with AI!” workflows and break them down [as Harper does] so [our viewers] can go “properly, that’s cool however I’m not utilizing vi and command-line instruments don’t play properly with Visible Studio, so I’ll simply steal your context hacks for working with huge 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 may construction among the “how I work” content material to particularly tackle completely different developer expertise ranges. For instance:
- Junior devs: deal with constructing that important analysis mindset and understanding when/the 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 submit modeled on Harper’s that we are able to publish right here on the O’Reilly Radar weblog) on the current name for shows hyperlink. We’ve up to date the submission deadline to March 12 and the occasion date from April 24 to Might 8 to present you a bit extra time to do your reasoning after which reply to this revised immediate.
On Might 8, O’Reilly Media might be internet hosting Coding with AI: The Finish of Software program Improvement as We Know It—a stay digital tech convention spotlighting how AI is already supercharging builders, boosting productiveness, and offering actual worth to their organizations. Should you’re within the trenches constructing tomorrow’s growth practices as we speak and focused on talking on the occasion, we’d love to listen to from you by March 12. You could find extra info and our name for shows right here.