diff --git a/.DS_Store b/.DS_Store deleted file mode 100644 index 5008ddfc..00000000 Binary files a/.DS_Store and /dev/null differ diff --git a/.gitignore b/.gitignore index aa7722e8..a22df410 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,5 @@ node_modules - +.DS_store /.cache /public/build /.netlify diff --git a/src/assets/yak_shaving.jpeg b/src/assets/yak_shaving.jpeg new file mode 100644 index 00000000..8f16b401 Binary files /dev/null and b/src/assets/yak_shaving.jpeg differ diff --git a/src/routes/drafts/psychological_pitfalls_of_ai_urgency.mdx b/src/routes/drafts/psychological_pitfalls_of_ai_urgency.mdx new file mode 100644 index 00000000..3e65bacf --- /dev/null +++ b/src/routes/drafts/psychological_pitfalls_of_ai_urgency.mdx @@ -0,0 +1,15 @@ +--- +meta: + title: "Psychological pitfalls of using artificial intelligence - a heightened sense of urgency" + description: Because AI can so quickly provide + dateCreated: 2026-05-06 + +tags: + - "ai" + - "software_engineering" +--- + +Something that I've found happening as I've started using AI tools more, especially agentic AI workflows, is that the AI very quickly comes back with a solution, and it puts me in this frenetic state where it feels like I need to make a decision on this thing now. + + +There's \ No newline at end of file diff --git a/src/routes/posts/agentic_ai_yak_shaving_on_steroids.mdx b/src/routes/posts/agentic_ai_yak_shaving_on_steroids.mdx new file mode 100644 index 00000000..7ad380fc --- /dev/null +++ b/src/routes/posts/agentic_ai_yak_shaving_on_steroids.mdx @@ -0,0 +1,39 @@ +--- +meta: + title: Agentic AI - yak shaving on steroids + description: The prospect of having agentic AI do all the real work means that we now focus on tuning the AI, not delivering the work. + dateCreated: 2026-05-23 + image: "yak_shaving" + +tags: + - "ai" + +--- +import yak_shaving from "@/assets/yak_shaving.jpeg"; + +I've been playing around with agentic AI for a side project recently, and I can absolutely see a world where the workflow is like this: + +1. I have an iterative session with an AI to define a feature - the outcome of this is an AI generated brief +2. The AI goes off and implements the feature, unsupervised, the outcome of this is a pull request. +3. I review the pull request - what I'm looking for is a cursory look over the code to check that the patterns are holding, and brief manual verification that the feature is working. + +_This is not my current workflow_ - that step 2. I have to supervise - because the AI goes off into rabbit holes and burns all my tokens and creates some messes. + +But this workflow seems tantalisingly in reach - whether that's all a fugazi is a different story. + +I have limited time. I work a full time job, and I have a four-year old and two four-month old babies, and I need to exercise. So with my side project, of which I'm about 40 hours in, I could spend my limited time chipping away at building new features, or I could spend it: + +- Optimising my prompts +- Adding lint rules and other guard rail test scripts +- Adding generation scripts + +All in the hope that at the end of it, in some future world - creating this application will be a delightful breeze - I'll be able to informally have a chat session with an AI, creating a list of features I want to see, and then come back the next night to review and merge the code it has created. + +ai generated image. A man is scoffing some pills while holding some shears. In the background are some yaks. The man is saying 'gonna go shave me some yaks' + + +This feels like yak-shaving. Perhaps this is another bit of software engineering wisdom that is disrupted by AI. + +The AI maximalist might argue that - 'This isn't yak shaving - this is what the job is now, you're not building products, you're building a factory that builds products'. + +This might be a case for a project at a high level of AI maturity - but for everything else there needs to be an appreciation that agnetic AI workflows will not be a free lunch. \ No newline at end of file