I believed I’d provide a number of takeaways and reflections based mostly on final week’s first AI Codecon digital convention, Coding with AI: The Finish of Software program Growth as We Know It. I’m additionally going to incorporate a number of quick video excerpts from the occasion. Should you registered for Coding with AI or should you’re an present O’Reilly subscriber, you may watch or rewatch the entire thing on the O’Reilly studying platform. Should you aren’t a subscriber but, it’s straightforward to begin a free trial. We’ll even be posting further excerpts on the O’Reilly YouTube channel within the subsequent few weeks.
However on to the promised takeaways.
First off, Harper Reed is a mad genius who made everybody’s head explode. (Camille Fournier apparently has joked that Harper has rotted his mind with AI, and Harper really agreed.) Harper mentioned his design course of in a chat that you simply would possibly need to run at half pace. His greenfield workflow is to start out with an concept. Give your concept to a chat mannequin and have it ask you questions with sure/no solutions. Have it extract all of the concepts. That turns into your spec or PRD. Use the spec as enter to a reasoning mannequin and have it generate a plan; then feed that plan into a unique reasoning mannequin and have it generate prompts for code technology for each the appliance and exams. He’s having a wild time.
Agile Manifesto coauthor Kent Beck was additionally on Staff Enthusiasm. He informed us that augmented coding with AI was “probably the most enjoyable I’ve ever had,” and stated that it “reawakened the enjoyment of programming.” Nikola Balic agreed: “As Kent stated, it simply introduced the enjoyment of writing code, the enjoyment of programming, it introduced it again. So I’m now producing extra code than ever. I’ve, like, 1,000,000 strains of code within the final month. I’m enjoying with stuff that I by no means performed with earlier than. And I’m simply spending an obscene quantity of tokens.” However sooner or later, “I believe that we received’t write code anymore. We’ll nurture it. It is a imaginative and prescient. I’m certain that lots of you’ll disagree however let’s look years sooner or later and the way all the pieces will change. I believe that we’re extra going towards intention-driven programming.”
Others, like Chelsea Troy, Chip Huyen, swyx, Birgitta Böckeler, and Gergely Orosz weren’t so certain. Don’t get me improper. They assume that there’s a ton of fantastic stuff to do and be taught. However there’s additionally numerous hype and unfastened considering. And whereas there can be numerous change, numerous present expertise will stay necessary.
Right here’s Chelsea’s critique of the current paper that claimed a 26% productiveness enhance for builders utilizing generative AI.
If Chelsea will do a sermon each week within the Church of Don’t Imagine All the things You Learn that consists of her exhibiting off varied papers and giving her dry and insightful perspective on how to consider them extra clearly, I’m so there.
I used to be a bit stunned by how skeptical Chip Huyen and swyx had been about A2A. They actually schooled me on the notion that the way forward for brokers is in direct AI-to-AI interactions. I’ve been of the opinion that having an AI agent work the user-facing interface of a distant web site is a throwback to display screen scraping—absolutely a transitional stage—and whereas calling an API can be one of the best ways to deal with a deterministic course of like cost, there can be an entire lot of different actions, like style matching, that are perfect for LLM to LLM. Once I take into consideration AI searching for instance, I think about an agent that has discovered and remembered my tastes and preferences and particular objectives speaking with an agent that is aware of and understands the stock of a service provider. However swyx and Chip weren’t shopping for it, no less than not now. They assume that’s a good distance off, given the present state of AI engineering. I used to be glad to have them carry me again to earth.
(For what it’s price, Gabriela de Queiroz, director of AI at Microsoft, agrees. On her episode of O’Reilly’s Generative AI within the Actual World podcast, she stated, “Should you assume we’re near AGI, strive constructing an agent, and also you’ll see how far we’re from AGI.”)
Angie Jones, however, was fairly enthusiastic about brokers in her lightning discuss about how MCP is bringing the “mashup” period again to life. I used to be struck specifically by Angie’s feedback about MCP as a type of common adapter, which abstracts away the underlying particulars of APIs, instruments, and knowledge sources. That was a robust echo of Microsoft’s platform dominance within the Home windows period, which in some ways started with the Win32 API, which abstracted away all of the underlying {hardware} such that utility writers not needed to write drivers for disk drives, printers, screens, or communications ports. I’d name {that a} energy transfer by Anthropic, apart from the blessing that they launched MCP as an open normal. Good for them!
Birgitta Böckeler talked frankly about how LLMs helped cut back cognitive load and helped assume via a design. However a lot of our every day work is a poor match for AI: giant legacy codebases the place we alter extra code than we create, antiquated know-how stacks, poor suggestions loops. We nonetheless want code that’s easy and modular—that’s simpler for LLMs to know, in addition to people. We nonetheless want good suggestions loops that present us whether or not code is working (echoing Harper). We nonetheless want logical, analytical, vital serious about drawback fixing. On the finish, she summarized each poles of the convention, saying we’d like cultures that reward each experimentation and skepticism.
Gergely Orosz weighed in on the continued significance of software program engineering. He talked briefly about books he was studying, beginning with Chip Huyen’s AI Engineering, however maybe the extra necessary level got here a bit later: He held up a number of software program engineering classics, together with The Legendary Man-Month and Code Full. These books are a long time previous, Gergely famous, however even with 50 years of device growth, the issues they describe are nonetheless with us. AI isn’t prone to change that.
On this regard, I used to be struck by Camille Fournier’s assertion that managers like to see their senior builders utilizing AI instruments, as a result of they’ve the abilities and judgment to get probably the most out of it, however usually need to take it away from junior builders who can use it too uncritically. Addy Osmani expressed the priority that fundamental expertise (“muscle reminiscence”) would degrade, each for junior and senior software program builders. (Juniors might by no means develop these expertise within the first place.) Addy’s remark was echoed by many others. No matter the way forward for computing holds, we nonetheless must know the best way to analyze an issue, how to consider knowledge and knowledge constructions, the best way to design, and the best way to debug.
In that very same dialogue, Maxi Ferreira and Avi Flombaum introduced up the critique that LLMs will have a tendency to decide on the commonest languages and frameworks when making an attempt to resolve an issue, even when there are higher instruments out there. It is a variation of the statement that LLMs by default have a tendency to supply a consensus resolution. However the dialogue highlighted for me that this represents a danger to talent acquisition and studying of up-and-coming builders too. It additionally made me marvel about the way forward for programming languages. Why develop new languages if there’s by no means going to be sufficient coaching knowledge for LLMs to make use of them?
Virtually all the audio system talked concerning the significance of up-front design when programming with AI. Harper Reed stated that this seems like a return to waterfall, besides that the cycle is so quick. Clay Shirky as soon as noticed that waterfall growth “quantities to a pledge by all events to not be taught something whereas doing the precise work,” and that failure to be taught whereas doing has hampered numerous tasks. But when AI codegen is waterfall with a quick studying cycle, that’s a really totally different mannequin. So this is a vital thread to drag on.
Lili Jiang’s closing emphasis that evals are far more complicated with LLMs actually resonated for me, and was in line with lots of the audio system’ takes about how a lot additional we have now to go. Lili in contrast an information science challenge she had performed at Quora, the place they began with a rigorously curated dataset (which made eval comparatively straightforward), with making an attempt to take care of self-driving algorithms at Waymo, the place you don’t begin out with “floor fact” and the fitting reply is very context dependent. She requested, “How do you consider an LLM given such a excessive diploma of freedom by way of its output?” and identified that the code to do evals correctly will be as giant or bigger than the code used to form the precise performance.
This completely suits with my sense of why anybody imagining a programmer-free future is out of contact. AI makes some issues that was arduous trivially straightforward and a few issues that was straightforward a lot, a lot tougher. Even should you had an LLM as choose doing the evals, there’s an terrible lot to be found out.
I need to end with Kent Beck’s considerate perspective on how totally different mindsets are wanted at totally different phases within the evolution of a brand new market.
Lastly, a giant THANK YOU to everybody who gave their time to be a part of our first AI Codecon occasion. Addy Osmani, you had been the proper cohost. You’re educated, an amazing interviewer, charming, and numerous enjoyable to work with. Gergely Orosz, Kent Beck, Camille Fournier, Avi Flombaum, Maxi Ferreira, Harper Reed, Jay Parikh, Birgitta Böckeler, Angie Jones, Craig McLuckie, Patty O’Callaghan, Chip Huyen, swyx Wang, Andrew Stellman, Iyanuoluwa Ajao, Nikola Balic, Brett Smith, Chelsea Troy, Lili Jiang—you all rocked. Thanks a lot for sharing your experience. Melissa Duffield, Julie Baron, Lisa LaRew, Keith Thompson, Yasmina Greco, Derek Hakim, Sasha Divitkina, and everybody else at O’Reilly who helped carry AI Codecon to life, thanks for all of the work you set in to make the occasion successful. And due to the just about 9,000 attendees who gave your time, your consideration, and your provocative questions within the chat.
Subscribe to our YouTube channel to look at highlights from the occasion or turn out to be an O’Reilly member to look at your complete convention earlier than the following one September 9. We’d love to listen to what landed for you—tell us within the feedback.