In growing the content material for our May 8 digital convention Coding with AI: The End of Software Development as We Know It, we couldn’t assist however wish to characteristic Harper Reed, whose current submit “My LLM Codegen Workflow ATM” so completely encapsulates the sort 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 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 straightforward for others to be taught from what he’s finished. It’s an important mannequin for the sort of data sharing we hope to engender with the upcoming occasion and others that may comply with. If you haven’t learn it but, go achieve this now.
In an e-mail to me, my outdated buddy Nat Torkington had this to say about Harper’s submit:
Learn 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 individual’s workflow
ALL of these 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 of us 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. But 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 Conference practically 30 years in the past, and that was a beloved characteristic of all our conferences thereafter).
Categories we’re desirous about embrace “my favorite AI tool,” “my favorite AI prompt or context hack,” “my workflow,” “my project that I would never have thought to try without the ease of experiment I get with AI,” and so forth. In addition to the lightning talks at this occasion, we’re additionally planning a future recurring occasion that’s completely dedicated to a dwell model of the sort of full show-and-tell that Harper did so properly.
So, go learn Harper, and present us what you’ve acquired! Ideally, you’ll not solely give us the complete model but additionally distill explicit, usable classes from it. Here’s some further knowledge from Nat’s e-mail to get you began:
The extra the mechasuit is designed on your cortex, the much less transferable it’s to different individuals. The threat is you begin with “here are six tools I use in my own complex workflow in a language you don’t recognise to solve problems you don’t have” and lose individuals in a flood of random software names.
[We want to be] in a position to take a look at totally different individuals’s “I code with AI!” workflows and break them down [as Harper does] so [our viewers] can go “well, that’s cool but I’m not using vi and command-line tools don’t play well with Visual Studio, so I’ll just steal your context hacks for working with big code bases in Copilot.”
Addy Osmani added to our e-mail dialog:
Building on the “ascending levels of nerd” framework (which I really like!), we might construction some of the “how I work” content material to particularly deal with totally different developer expertise ranges. For instance:
- Junior devs: concentrate on constructing that crucial analysis mindset and understanding when/how you can 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 will publish right here on the O’Reilly Radar weblog) on the present name for shows hyperlink. We’ve up to date the submission deadline to March 12 and the occasion date from April 24 to May 8 to present you a bit extra time to do your reasoning after which reply to this revised immediate.
On May 8, O’Reilly Media can be internet hosting Coding with AI: The End of Software Development as We Know It—a dwell digital tech convention spotlighting how AI is already supercharging builders, boosting productiveness, and offering actual worth to their organizations. If you’re within the trenches constructing tomorrow’s growth practices right now and desirous about talking on the occasion, we’d love to listen to from you by March 12. You can discover extra data and our name for shows right here.