Hamilton Greene @sirhamy.bsky.social · 10/10/2026Spend Elon Musk's Money - labs.hamy.xyz/labs/spend-m... 000
Hamilton Greene @sirhamy.bsky.social · 10/10/2026To commemorate Elon becoming a trillionaire (again) I added new items to Spend Elon's Money: - Fund GTA 7 - The Las Vegas Strip - The NFL - Every Disney Park - Costco And much, much more! 100
Hamilton Greene @sirhamy.bsky.social · 09/10/2026AI Dotfiles - How I Take My AI Workflows Across Projects And Machines - hamy.xyz/blog/2026-09... 000
Hamilton Greene @sirhamy.bsky.social · 09/10/2026My AI setup keeps skills in .agents/ and instructions in agents.md. CLAUDE.md and .claude/skills symlink so I only have one source of truth for my AI workflows. 310
Hamilton Greene @sirhamy.bsky.social · 08/10/2026GPT 6.1 Sol may not be as smart or fast as Opus 5.5 but I get a lot more usage with it. As frontier models become "good enough" for most tasks, price and convenience factor more into model choice. Competition is good for consumers and I expect inference price per intelligence to continue to fall. 010
Hamilton Greene @sirhamy.bsky.social · 08/10/2026Durable Context, Disposable Code - Building Systems with Speed and Quality in the Agentic Era - hamy.xyz/blog/2026-10... 000
Hamilton Greene @sirhamy.bsky.social · 08/10/2026My hypothesis for speeding up the SDLC to get: - Speed of agents - Quality of humans - Solid alignment + understanding of system is to make the code disposable and the context durable. 100
Hamilton Greene @sirhamy.bsky.social · 05/10/2026How Much Faster is Coding with AI Agents? (from a Senior Software Engineer) - hamy.xyz/blog/2026-07... 000
Hamilton Greene @sirhamy.bsky.social · 05/10/2026PRs aren't a good proxy for impact: - 1 PR could change 1 line and yield massive business impact - another could be 10k lines and cause an incident. I use PR count to compare my own throughput over time, not to measure value. 100
Hamilton Greene @sirhamy.bsky.social · 04/10/2026Why I'm moving from C# to Rust for High-level Apps - hamy.xyz/blog/2026-02...hamy.xyzWhy I'm moving from C# to Rust for High-level Apps - HAMYEssay - Published: 2026.03.04 | 6 min read (1,697 words)build | create | csharp | rust 010
Hamilton Greene @sirhamy.bsky.social · 04/10/2026I migrated my blog from C# to Rust in a couple hours. It came out to be 4x faster and use 4x less memory for the same logic and data. But performance isn't even the main reason I switched - the types and tooling are even more important. 120
Hamilton Greene @sirhamy.bsky.social · 30/09/2026With AI, Your Imagination is the Limit - hamy.xyz/blog/2026-09... 000
Hamilton Greene @sirhamy.bsky.social · 30/09/2026AI 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 · 30/09/2026Rust is a great language for agentic engineering: - Expressive types + compiler hints - Mainstream + well-supported - Great performance hamy.xyz/blog/2026-04...hamy.xyzWhy High-Level Rust Wins Over Other High-Level Languages for Agentic Engineering - HAMYEssay record 100
Hamilton Greene @sirhamy.bsky.social · 29/09/2026How Much OpenCode + GPT 5.6 Usage Do You Get With OpenAI's ChatGPT Pro Subscription? - hamy.xyz/blog/2026-07... 001
Hamilton Greene @sirhamy.bsky.social · 29/09/2026My $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 200
Hamilton Greene @sirhamy.bsky.social · 27/09/2026I 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 · 26/09/2026Porting my F# Web App to Rust in 2 Hours with AI - hamy.xyz/blog/2026-08... 000
Hamilton Greene @sirhamy.bsky.social · 26/09/2026My 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 · 24/09/2026I think the open weight models will catch up enough that we just drop off frontier to those. Competition is good. Bubble will pop but we'll be left with the technology. 000
Hamilton Greene @sirhamy.bsky.social · 23/09/2026I built a multiplayer Game of Life with Rust + Datastar 000
Hamilton Greene @sirhamy.bsky.social · 17/09/2026A 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 · 15/09/2026AI 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 · 15/09/2026Why Rust Wins in the Age of AI - hamy.xyz/blog/2026-04...hamy.xyzWhy Rust Wins in the Age of AI - HAMYEssay - Published: 2026.04.15 | 4 min read (1,198 words)create | rust 000
Hamilton Greene @sirhamy.bsky.social · 15/09/2026Which 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 · 12/09/2026My 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 · 09/09/2026How 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 · 05/09/2026AI 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 · 04/09/2026Why I'm moving from C# to Rust for High-level Apps - hamy.xyz/blog/2026-02...hamy.xyzWhy I'm moving from C# to Rust for High-level Apps - HAMYEssay - Published: 2026.03.04 | 6 min read (1,697 words)build | create | csharp | rust 000
Hamilton Greene @sirhamy.bsky.social · 04/09/2026Rust 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 · 04/09/2026I'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 · 02/09/2026Fable 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 · 29/08/2026Initial 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 · 26/08/2026My 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 · 24/08/2026Humans 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 · 15/08/2026AI 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 · 15/08/2026Why Rust Wins in the Age of AI - hamy.xyz/blog/2026-04...hamy.xyzWhy Rust Wins in the Age of AI - HAMYEssay - Published: 2026.04.15 | 4 min read (1,198 words)create | rust 000
Hamilton Greene @sirhamy.bsky.social · 15/08/2026For 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 · 12/08/2026I'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 · 05/08/2026My 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 · 04/08/2026Why I'm moving from C# to Rust for High-level Apps - hamy.xyz/blog/2026-02...hamy.xyzWhy I'm moving from C# to Rust for High-level Apps - HAMYEssay - Published: 2026.03.04 | 6 min read (1,697 words)build | create | csharp | rust 000
Hamilton Greene @sirhamy.bsky.social · 04/08/2026I 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 · 31/07/2026OpenCode 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 · 29/07/2026My 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 · 29/07/2026My 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 · 27/07/2026My 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 · 25/07/2026My 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 · 24/07/2026You 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 · 23/07/2026The 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 · 22/07/2026Why High-Level Rust Wins for Agentic Engineering - hamy.xyz/blog/2026-04...hamy.xyzWhy High-Level Rust Wins Over Other High-Level Languages for Agentic Engineering - HAMYEssay - Published: 2026.04.22 | 5 min read (1,260 words)artificial-intelligence | create | rust 000
