Making Ideas To Impact
Every HTTPS connection on the modern web uses TLS. Not SSL. The padlock icon in browsers still says SSL. Hosting providers sell SSL certificates. Devops teams talk about SSL termination. But SSL has been dead since 2015. What actually protects traffic is TLS 1.2 or TLS 1.3.
This distinction matters. SSL and TLS are not the same protocol. They have different security properties. Different handshake flows. Different cipher suites. One of them has known vulnerabilities that attackers can exploit.
The most-said line in my group chats this week was three words: “I miss Fable.”
Not in a nostalgic way. In a “my entire workflow is broken” way.
Fable was the model I used for first-draft generation. Fast, cheap, good enough for 80 percent of the work. Then it vanished. No deprecation warning. No migration path. Just gone.
My first reaction was what a lot of people are doing now: go local. Buy a GPU, run llama.cpp, never depend on a vendor again. I spent $1,400 on a used RTX 4090. I downloaded 150GB of model weights. I learned to love the sound of my fans spinning at 80 percent.
For one month, self-hosting worked. Then the novelty wore off.
The 4090 draws 450W under load. My electricity bill went up $35. The 70B models I was running maxed out at 32K context — not enough for full codebase reviews. Batch processing hundreds of documents meant queuing jobs overnight. And when Opus 4.8 dropped with significantly better reasoning, I had no way to access it without going back to cloud anyway.
I was renting infrastructure, not avoiding vendors. The landlord just changed from Anthropic to NVIDIA.
Then I tried DeepSeek V4 Pro on Ollama Cloud. The pricing made me reconsider everything.
SpaceX is reportedly buying Cursor for $60 billion. Anthropic is shipping Claude Code updates every two weeks. Every developer I know is asking the same question: which one should I actually use?
I spent the last 90 days shipping production code with both. Not toy projects. Not benchmarks. Real features, in a real codebase, with real deadlines. Here’s what each one is actually good at — and where they both fail you.
I’m not going to give you a feature table. You’re smart enough to read the docs yourself. What I am going to do is tell you what happened when I made each tool do real work.
Six weeks ago, my AI coding agent was producing garbage. Not bad code — garbage. Functions that compiled but did nothing. Tests that passed for the wrong reasons. Refactors that introduced three bugs while fixing one.
I spent two days debugging the agent. Then I spent a week rebuilding it. Then I realized the problem wasn’t the agent.
The problem was me.
This is the story of what I changed. Not the agent — me.
My homelab AI agent setup was costing $42/month in API calls alone — until I switched to local quantized models.
That number came straight from my OpenRouter billing dashboard for April 2026: 350,000 tokens across Claude 3 Haiku and Mistral Small, mostly from my personal agent that checks GitHub notifications, drafts tweets, and summarizes my daily reading. At $0.00012 per 1K tokens for Haiku and $0.00006 for Mistral, the math added up fast. I’d told myself local LLMs weren’t ready for prime time — too slow, too finicky, too much VRAM — until I hit a psychological wall: paying for something I could run myself felt like renting a bicycle when I owned a garage full of parts.
I decided to fix it. Over three weekends, I rebuilt my agent pipeline around Ollama, quantized Llama 3 models, and deliberate GPU time-slicing. The result? My monthly LLM API spend dropped to $0. building practical AI agents for real-world automation — My agent still handles the same tasks — sometimes faster, sometimes slower, but consistently useful. Along the way I learned concrete lessons about optimizing AI agent performance with structured prompts, quantization tradeoffs, containerized GPU sharing, and why “local first” doesn’t mean “local only.”
Here’s exactly what I did, what I measured, and what broke along the way.
Most “responsible AI” content reads like it was written by a policy team that has never deployed an agent to production. The checklists are long. The principles are abstract. And none of them tell you what to do when your agent starts hallucinating customer data at 3 AM and the on-call engineer is asleep.
I have been building AI agents for about a year now. Not research. Not demos. Actual agents that touch real data, make real decisions, and occasionally break things in ways I did not anticipate. Here is what responsible AI looks like from the builder’s side — not the policy side.
—