Hrushikesh Pawar — Technical essays on learning systems, code intelligence, and evaluation.

last build: 2026-07-20 · 4 essays queued · motif: models · systems · evidence

hrushikesh@site:~$ whoami

I build production AI systems. This is where I reconstruct the theory behind them, test claims about coding agents and migrations, and publish the derivations, experiments, and failures.

hrushikesh@site:~$ ls

hrushikesh@site:~$ essays --claims

The Imitation Game Was Never a Benchmark [in-progress]

claim: Turing did not give us a universal leaderboard for intelligence. He replaced an underspecified metaphysical question with an operational experiment — modern debates about whether LLMs think or reason are therefore largely debates about constructs, protocols, judges, and alternative explanations.

Bun's Zig-to-Rust Rewrite Was Not a Prompt [planned]

claim: The interesting unit in Bun's rewrite is not the model call. It is the closed-loop migration system: a porting specification, an externalized lifetime analysis, task sharding, compiler feedback, a language-independent test oracle, adversarial review, and continuous human supervision.

Do Coding Agents Need Code Graphs? [planned]

claim: "Graphs understand repositories" and "grep is enough" are both underspecified claims. A representation is useful only if it helps a system retrieve change-relevant context more accurately or cheaply under a fixed budget.

How Neural Networks Learn [planned]

claim: Backpropagation is not a mysterious brain-inspired learning rule. It is an efficient application of the chain rule to a composed computation. The conceptual path from a perceptron to a multilayer network is a path from linear decision geometry to differentiable representation learning.

hrushikesh@site:~$