October 6, 2026

What would a useful agent be like?

I use coding agents for basically all of my day day to work now. Recently I’ve been seeing more and more consumer-facing agent-like products and have been trying them out but find none are really able to do the things I want, mostly because they are all run by sketchy tech megacorps that I don’t trust and don’t want to connect my data to. Unfortunately Siri still really sucks, but in theory it’s more in the realm of what I actually want and Apple already owns my entire digital life anyway. […3 min read]

post#agent-driven-development#ai-agents#digital-assistants#llms#personal-agents#personal-knowledge-management#productivity#self-hosting

September 7, 2026

There usually isn't a correct answer

Writing software with AI is a really different experience than writing it by hand. Before coding agents, software was expensive to produce, in the sense that it required a lot of time from a lot of highly skilled and highly compensated people. Now, generating code is very cheap comparatively speaking, and the expensive part is deploying, operating, and maintaining it. People say AI can do this too but my experience in the industry is that it can’t, which I think is mostly why software engineers still have jobs and are actually more in demand than ever. This only makes it more important to choose wisely what software is worth producing in the first place. […3 min read]

post#agent-driven-development#ai#ai-agents#complexity#productivity#quality#software-development#software-engineering

August 8, 2026

Is it all just vapourware?

Maybe I’m just too cynical but it’s really starting to feel like more or less all of this new “AI”/agent software is vapourware. I’ve been trying to take this whole “agentic development” thing seriously and there is just so much friction in this ecosystem it’s absolutely insane. It’s very clear that all this stuff is built by engineers who a) have free access to unlimited tokens and b) have no systematic review or QA process for usability testing or dogfooding their products except on the most straightforward of happy paths. […3 min read]

post#agent-driven-development#agent-tools#ai#ai-agents#ai-hype#software-engineering#vapourware

August 2, 2026

Have the models come full circle?

It feels like the big LLMs have come full circle. At first they were too naive to implement meaningful features autonomously and took so much handholding to get anything done it was quite a pain babysitting them. Then they got good enough to do meaningful software engineering work and there was (I now recognize in hindsight) a sweet spot at some point early this year where they got meaningfully better and good enough to take non-trivial work off my hands without causing dramatically more work. But now they're far too eager and require constant babysitting again. […2 min read]

post#agent-driven-development#ai-agents#ai-hype#ai-safety#coding-agents#developer-workflow#llms#software-engineering