For what it's worth, I really enjoy superpowers. In particular, it does a great job with TDD that stops the model from jumping to conclusions, and I've been able to get it, even with Opus, to execute on much longer specs quite well.
In addition to what other people have said, I've taken some time to do leetcode questions lately - both architecture ones and coding ones. I'm not looking for a job by any stretch, but the practice and forcing a detailed zoom in has been really cathartic, and leetcode gives a nice structure/feeling of progress to it.
This will be really powerful for voice. Being able to reason makes LLM so much smarter but with voice your latency budget is so tight that you can't spare the time typically.
I really love using AI to code but more and more I wonder ... Are things really that different? So I guess I'm the business as usual type.
I think on the frontend side we're going to see a lot more scope for teams.
On a backend infra side it seems as hard as ever. Still have to think really hard problems, think deeply about data structure and flow, and deal with second- and third-order effects. Or even harder because the models like to confidently lie.
The harder question is how we train people but that doesn't seem insurmountable either. Most of us cut our teeth as junior engineers somewhere, implementing tasks that Claude can now do without breaking a sweat but was that really the most efficient way to train and learn?
I'm also a lifelong vim user. I guess what I'm getting at is that I find the journey even more engaging now. I think I'm a good programmer. I've worked at great companies. I was competitive in ACM contests and Top Coder. But I find the journey even more engaging now because I can focus on really, really deeply understanding something, and less time on glue. Writing code by hand is still fun, don't get me wrong, but I'm also enjoying the step change in scale.
I don't think IDEs as they exist today are necessarily the right abstraction anymore anyway, to the extent they ever were. At least any more than a C++ IDE that was centered on assembly language as the main thing would be. I want data models, API contracts, and data flows. I don't know what the right answer is, but I think there's something coming.
I get to spend more time working on the things I enjoy. For example, data modeling and workflow orchestration, and building product to solve customer problems. And really, that comes down to spending a lot of my time just thinking really hard - because once I have a clear plan, it's actually not that hard to build it. Not only that, but I can build something, react to it, rebuild it, react to it, and come up with something I think is much better than I would have been able to build myself. Not to mention much faster.
I honestly don't get it - how isn't everyone having a blast with AI? Every one of those side projects you never had time for you can build in a weekend. You can explore five ideas at once. You can do big refactors/cleanups you'd never be able to dream of in the past. As a software engineer it's been fantastic.
AstraZeneca is doing some really interesting research in this area - cell therapies that reset the immune system to eliminate the dysfunctional cells driving autoimmune disease, and then allow a healthy immune system to rebuild (for diseases like lupus, rheumatoid arthritis, and multiple sclerosis).
I feel so many of these. LOL @ GitHub endorse-ish, more -ish every day now. Overall though seems like a pretty good hit rate.
Surprised to see datadog as a regret - it is expensive but it's been enormously useful for us. Though we don't run kubernetes, so perhaps my baseline of expensive is wrong.
As I've been looking at this problem from a different angle, I wonder how much execution and planning should be coupled. Once we have specs in GitHub, for example, it feels like we can use whatever tool to execute on them.
https://github.com/purplefish-ai/factory-factory - creating an IDE for managing a swarm of claude agents, and more importantly, increasingly baking workflows into them (e.g. design -> build -> review -> push -> address comments).
Purplefish | https://purplefish.com/careers | Member of Technical Staff | Full-Time | ONSITE | New York, NY, USA | NextJS, Typescript, Python | $150k-$225k + 0.5%+
Purplefish is transforming the trillion-dollar talent industry with powerful AI agents that will fully automate most hiring processes end-to-end.
We are funded by 8VC, and Adam and I previously worked closely together to launch 145 companies at the venture studio Fractal Software out of a $650 million fund. Before that I was a staff software engineer at Lyft, and Adam was CRO at Wunderkind ($100m+ ARR). We've built a powerful voice agent, and are expanding into other parts of the sourcing-to-onboarding flow. We have customers, revenue is growing, and so is our team.
We're currently a team of 3 engineers in NYC (9 people total). We're working on really cool problems with multimodal AI agents (and some really not cool problems like ATS and HRIS integrations). I'm trying to build the engineering team that I would want to join, which to me means a high emphasis on agency, purpose, technical excellence, collaboration, learning and velocity. Recently A16Z mentioned us in the state of voice AI report: https://a16z.com/ai-voice-agents-2025-update/
We're building on LiveKit's agents framework, Python, and NextJS. We're having a lot of fun and having real positive impact on our customers' businesses.