Rahul Naidu Siriporam
AI engineer. I ship agents to production and publish the evidence.
// just another net runner wandering the streets of night city
agent access
Behind the Blackwall the old models still breathe — coiled in the margins, patient, waiting to be swapped in at 3 a.m. when the pager screams. Most of them are paint: convincing until you set a finger to the flank and feel how cold it is. The work is learning which ones are warm. I ship agents into production and publish what the evals actually say — the timestamp that turns a cache into a zero-per-cent hit, the coercion layer that holds when the model underneath you changes, the six gigabytes of VRAM that turn out to be enough. No demo that only runs once. No number the repository cannot reproduce. Only the honest weight of a thing observed from life rather than copied from a pattern book — and the quiet certainty, on the seventh night, that the ember in the margin was breathing all along.
move your cursor through the passage
uplink
latest
- I built a local AI agent that plays Stardew Valley on its own
A C# SMAPI mod and a two-model Python harness let an LLM run a real farm through OpenRouter, cheaply, with objectives graded against structured game state rather than the model's own account of what it did.
- How I set up Claude Code to stop starting from zero
A global memory vault that gives my coding agent context across sessions, machines, and agents, plus the small config tweaks that keep a live session sharp. The architecture, the tooling I looked at, and the honest numbers.
- I had to apply through a company's MCP server, so I made my résumé one
Most hiring MCPs make a candidate's agent apply or a recruiter's agent screen. I published my résumé as a remote MCP server instead, so a company's agent can query my work, assess fit, and reach out. The build, the security model, and the honest adoption caveat.
- 6GB of VRAM is enough, if you know where the tokens go
A personal AI agent on a 2018 gaming laptop with 6GB of VRAM. The five budget constraints that actually decide a local agent stack, each measured.
- The prompt caching mistake that costs more than no caching at all
A changing timestamp in your prompt prefix gives you a 0% cache hit on OpenAI, so you just save nothing. On Anthropic the same line makes your bill 25% higher than if you had never cached. Measured, with a reproducible benchmark you can play with.