iiinova — where your digital self keeps evolving

Hamilton Greene @sirhamy.bsky.social · 30/09/2026

AI is the present and future of knowledge work. - Implementation was a major bottleneck in every domain - AIs commoditize implementation Your imagination is now the limit.

100

Hamilton Greene @sirhamy.bsky.social · 30/09/2026

Rust is a great language for agentic engineering: - Expressive types + compiler hints - Mainstream + well-supported - Great performance hamy.xyz/blog/2026-04...

hamy.xyz

Why High-Level Rust Wins Over Other High-Level Languages for Agentic Engineering - HAMY

Essay record

100

Hamilton Greene @sirhamy.bsky.social · 29/09/2026

My $100/month ChatGPT Pro plan projects to ~$2,200/month in API value, but that doesn't mean AI subs are unsustainable: • ~60% estimated inference margins • Most people don't use full quotas • Subs can drive enterprise adoption

100

Hamilton Greene @sirhamy.bsky.social · 27/09/2026

I think it's inevitable we'll end up with software factories writing 99%+ of code. - AI is good enough and improving - Much faster at reading / writing / validating - Frees bandwidth for humans to focus on direction and improving guardrails

000

Hamilton Greene @sirhamy.bsky.social · 26/09/2026

My agent workflow has one supervisor, one task per build-and-review cycle, and one decision after each result: continue, repair, or block. It costs more tokens than active prompting but requires less attention from me.

100

Hamilton Greene @sirhamy.bsky.social · 23/09/2026

I built a multiplayer Game of Life with Rust + Datastar

000

Hamilton Greene @sirhamy.bsky.social · 17/09/2026

A lot has changed about my AI coding setup in the last year: - I haven't edited a line of code in 6 months - Default to agentic engineering - Using GPT + OpenCode - Talk to my computer more than type - Increased throughput ~2x

030

Hamilton Greene @sirhamy.bsky.social · 15/09/2026

AI creates 100% of my code now. • I drive - direction, priorities, design decisions, code reviews • AI works - research, writing code, reviewing code, docs. I haven't edited a line of code in months and at this point I don't really see that changing.

100

Hamilton Greene @sirhamy.bsky.social · 15/09/2026

Which language is best for AI coding depends on how you measure: - One-shot prompts: Python/Ruby/Go win by 1.5x on speed/cost - Iterative agentic loops: Rust wins on quality/correctness Compiler loops pay dividends across thousands of agentic cycles.

110

Hamilton Greene @sirhamy.bsky.social · 12/09/2026

My AI agent day-night cycle: • 16:00-17:00: close loops and kick off agents • 20:00-20:30: Kick off another turn • Next morning: review a few extra PRs' worth of overnight work

000

Hamilton Greene @sirhamy.bsky.social · 09/09/2026

How I reuse AI workflows across machines: • Keep skills in an AI dotfiles repo • Load it into home directory Dotfiles but for AI workflows.

000

Hamilton Greene @sirhamy.bsky.social · 05/09/2026

AI hasn't made my whole software engineering job 3x faster but it has made one major part of it - coding - about 3x faster. Planning, priorities, coordination, design, and review still constrain the whole system.

010

Hamilton Greene @sirhamy.bsky.social · 04/09/2026

Rust got many of the core, hard-to-change things right at the outset: - Expressive types - Tooling with cargo and clippy - Near-metal performance These are things you can't easily retrofit and makes Rust very appealing in the age of AI.

100

Hamilton Greene @sirhamy.bsky.social · 04/09/2026

I've spent years searching for a programming language with: - Expressive types - Big ecosystem - Large community - Good performance - Good Devx Here's my ranking across 15 of the most popular languages: hamy.xyz/blog/2026-01...

100

Hamilton Greene @sirhamy.bsky.social · 02/09/2026

Fable 5.1 looks interesting but it's still a slow and expensive model. For most agentic engineering situations I think GPT 5.6 Sol is still a better balance of intelligence, cost, and speed.

000

Hamilton Greene @sirhamy.bsky.social · 29/08/2026

Initial experiments reveal that Open AI's subscription plan is heavily subsidized: • Subscription plan: $100/month GPT Pro • API cost: ~$550/week or ~$2,200/month

000

Hamilton Greene @sirhamy.bsky.social · 26/08/2026

My 2-hour AI migration result: • 1,918 lines of F# became 2,359 lines of Rust • The app built and ran locally • But deploy was borked and AI added a _lot_ of verbosity to the site copy

000

Hamilton Greene @sirhamy.bsky.social · 24/08/2026

Humans drive the agent, agent drives the tools. - Humans - Declare intent / purpose - Agents - Decide how to accomplish it, fan out to tools - Tools - Provide deterministic info / feedback Improve the system each cycle. hamy.xyz/blog/2026-06...

000

Hamilton Greene @sirhamy.bsky.social · 15/08/2026

AI creates 100% of my code now. I haven't written or edited a line of code in months. The closest I get is writing my blog posts which I happen to do in the same editor (nvim btw).

000

Hamilton Greene @sirhamy.bsky.social · 15/08/2026

For one-shot prompts Ruby, Python, and Go are 1.5x faster and cheaper than Rust (ai-coding-lang-bench). But real agentic work is iterative. That's where Rust's compiler loop (expressive types, ownership) shines. These guardrails scale correctness to large codebases, orgs, and teams of agents.

140

Hamilton Greene @sirhamy.bsky.social · 12/08/2026

I'm trying to lean into a day/night cycle with agents where I let them cook while I'm AFK. I close loops at 16:00, check agents again at 20:00, then review their overnight work the next day.

000

Hamilton Greene @sirhamy.bsky.social · 05/08/2026

My average coding throughput across 3 phases: • Before AI agents: 7 PRs/week • Early agents: 12 PRs/week • Current workflow: 20 PRs/week That's roughly 3x my manual baseline and almost 2x my early agent workflow.

020

Hamilton Greene @sirhamy.bsky.social · 04/08/2026

I tried Rust years ago to build a simple CSV parser and got absolutely nowhere in an hour. Then rewrote the same thing in Python in 15 minutes. But fastforward to 2026 and AI is now a 24x7 tutor and coworker which vastly improves the infamous learning curve.

100

Hamilton Greene @sirhamy.bsky.social · 31/07/2026

OpenCode web can power the same build-from-my-phone workflow as Claude Code remote control, but setup is more manual: • Secure access via Tailscale • Scripted startup + recovery It works, but I wouldn't recommend it unless you're comfortable scripting your computer.

010

Hamilton Greene @sirhamy.bsky.social · 29/07/2026

My current AI model split: • GPT 5.6 Terra / Sol for general coding and reference work • Claude Opus for subjective writing and UI • Claude Fable almost never (too slow + expensive, only for truly hard things) • Human review for the final acceptance / translation

000

Hamilton Greene @sirhamy.bsky.social · 29/07/2026

My first 3 days with OpenCode + GPT 5.6 Sol on Open AI's $100/month GPT Pro Plan: • 75% of weekly quota used • 407M logged tokens • ~$413 API-equivalent usage at ~90% input cached.

000

Hamilton Greene @sirhamy.bsky.social · 27/07/2026

My early GPT 5.6 vs Claude results: • Tasks that would take Claude 30s-minutes to return data for are almost immediate • Usage looks 2-3x cheaper • Sol is practical enough to use way more often than Fable Early anecdotal data but looks very promising for a daily driver.

100

Hamilton Greene @sirhamy.bsky.social · 25/07/2026

My AI setup is becoming model agnostic: • Terminal-based workflows • Skills shared across harnesses • Models and providers that are swappable via config

100

Hamilton Greene @sirhamy.bsky.social · 24/07/2026

You drive, let agents do the footwork. - Humans - strategy, vision, systems, and guardrails. - Agents - research, reading, writing, and coding. Keep to 1-2 tasks at a time, use agents to fanout underneath. hamy.xyz/blog/2026-06...

000

Hamilton Greene @sirhamy.bsky.social · 23/07/2026

The AI labs tend to one-up each other every few months. A model-agnostic setup lets me keep the same workflows and swap the model or harness when the leader changes. I think that flexibility will prove to be a competitive advantage over time.

000

Hamilton Greene @sirhamy.bsky.social · 22/07/2026

- Go: fast, but no sum types allows more logic bugs - TypeScript: huge ecosystem, but types are unsound (Zod, any, as x) - OCaml/Haskell: great types, but AI writes non-idiomatic code - Rust: expressive types, compiler hints, and AI writes well

220

Hamilton Greene @sirhamy.bsky.social · 16/07/2026

What I actually spend on AI as an engineer: • Work: ~$4k/month (~$50k/year), nearly all Claude Opus • Personal: ~$200/month on Max 20x. The difference is mostly hours / day (8h at work, 0-2h personal) and having access to subsidized sub pricing.

000

Hamilton Greene @sirhamy.bsky.social · 16/07/2026

I built a simple calculator for how I'm thinking about AI token spend ROI. Example calc: - Your cost: $100k - AI cost: $50k - Speedup: 1.6x - Your value with AI = $100k x 1.6 = $160k - AI value = $160k - $100k = $60k - Net value = $60k - $50k = $10k hamy.xyz/blog/2026-07...

000

Hamilton Greene @sirhamy.bsky.social · 15/07/2026

SWE-bench Multilingual tested agents across 9 languages and Rust came out on top for task completion. Rust isn't the fastest or cheapest for AI generation - Python, Go, and Ruby win that. But the extra time spent iterating against types/compiler/linter turns out to be a feature, not a bug.

100

Hamilton Greene @sirhamy.bsky.social · 11/07/2026

AI is getting so good at writing standard code that it starts to look like a natural language abstraction on top of programming languages. This changes the calculus from why would I use x to why would I not use x? Rust has great perf, types, and ecosystem. With AI, it has great devx, too.

100

Hamilton Greene @sirhamy.bsky.social · 10/07/2026

TL;DR - In 2026.H1, I started feeling like a real dad, took parental leave, went to a programming retreat, shipped CloudSeed Rust + QuietCut, reached 130k views, got back to building for fun, and started an AI diet. hamy.xyz/blog/2026-h1...

000

Hamilton Greene @sirhamy.bsky.social · 09/07/2026

Rust's learning curve is overexaggerated. Most of the pain comes from fighting the borrow checker when you don't need to. Write high-level Rust — immutable data, cheap clones, service traits — and it all fits together.

100

Hamilton Greene @sirhamy.bsky.social · 08/07/2026

My favorite way to organize hypermedia endpoints is Backend for Frontend: - /PAGE - renders full page - /PAGE/ACTION - Performs action, renders appropriate component Reuse coarse-grained components across page actions. Rust + Datastar - hamy.xyz/blog/2026-03...

hamy.xyz

Getting Started with Datastar - Build a Rust + Axum Todo App - HAMY

Essay - Published: 2026.04.08 | 8 min read (2,048 words)build | create | datastar | rust

000

Hamilton Greene @sirhamy.bsky.social · 04/07/2026

Rust is a great high-level language if you abide by a few rules: - Immutable data - Functional pipelines - Cheap clones - Arc dyn traits for dependency injection After a couple weeks (and the help of AI) I got the devx competitive with C# and TS.

110

Hamilton Greene @sirhamy.bsky.social · 03/07/2026

I think talking will become the primary means of driving computers simply because it's the path of least resistance. I think of my mom, brother, and wife who still poke type and how much easier it's going to be for them to talk vs type large text blobs.

100

Hamilton Greene @sirhamy.bsky.social · 27/06/2026

Anecdotal results of agentic engineering: - Before: I shipped 1-2 PRs a day, averaging ~7 a week - After: I ship 2-3 PRs a day, averaging ~12 a week So my guesstimate is a 50-60% speed improvement over my previous workflows. hamy.xyz/blog/2026-06...

000

Hamilton Greene @sirhamy.bsky.social · 25/06/2026

How I build vertical slices with agents: - Build slices of atomic commits e2e - Iterate to get desired behavior - Push bottom commits to stacked PRs - Regen stack based on feedback / improvements hamy.xyz/blog/2026-06...

000

Hamilton Greene @sirhamy.bsky.social · 24/06/2026

How I Balance Speed, Quality, and Mental Overhead in Agentic Engineering - Drive strategy, systems, and vision - Let agents do the footwork quickly - Do 1-2 things at a time and improve the system each cycle hamy.xyz/blog/2026-06...

000

Hamilton Greene @sirhamy.bsky.social · 22/06/2026

If agents are going to write the code anyway, why not pick the most reliable language? Python agents ship fast but fragile. Rust agents ship fast and correct - compiler catches ownership, lifetimes, and invalid states before runtime. Shift left is MORE important with agentic engineering.

210

Hamilton Greene @sirhamy.bsky.social · 20/06/2026

QuietCut - a CLI that removes silence from videos: - Most of my videos are single take, talking head - This cuts editing time down to a single CLI call - Runs local, no subs hamy.xyz/notes/quietcut

000

Hamilton Greene @sirhamy.bsky.social · 18/06/2026

The future of work with autonomous agents is like gardening: - Design the architecture, set the scaffolding, plant the seeds (tasks) - Set the agents loose - Leave and let things grow - Come back and tend to the system - inspect, refine, and redirect

110

Hamilton Greene @sirhamy.bsky.social · 16/06/2026

I built a game where you spend Elon Musk's money: labs.hamy.xyz/labs/spend-m...

020

Hamilton Greene @sirhamy.bsky.social · 15/06/2026

Why Rust pairs well with AI agents: - Expressive types make invalid states unrepresentable - Ownership + lifetime rules prevent runtime bugs like stale data and unexpected mutations The compiler becomes the deterministic check on nondeterministic AI output.

100

Hamilton Greene @sirhamy.bsky.social · 11/06/2026

High-level Rust can get you most of the language's benefits with a much smoother devx experience but there are some serious gotchas when writing Rust like a high-level, GCed language: - Clones can be unexpectedly expensive (3-5x of GC langs) - Async starvation is possible and easy to do

110

Hamilton Greene @sirhamy.bsky.social · 09/06/2026

Everything you need out of the box but nothing you don't. CloudSeed Rust: Axum API, passwordless magic link auth, Postgres-backed job queue, Maud SSR, Tailwind + DaisyUI - spin up a fullstack Rust webapp in minutes.

420