Writing by Viksit Gaur
Optimizing Tool Selection for LLM Workflows: Differentiable Programming with PyTorch and DSPy
Update: Trended on Page 1 on HN for the whole weekend! Part 2 coming soon! Thanks for all the feedback. Hackernews discussion How local, learnable routers can reduce token overhead, lower costs, and bring structure back to agentic workflows. Modern…
From Prompts to Programs: Why We Need a Compiler for LLMs
Early computing started with logic gates. We wrote in binary because we could reason about how bits flowed through circuits. As complexity grew, we invented assembly languages to abstract over machine code: still low-level, but easier to manage…
Three Futures for AI
We’re racing toward something. Whether it’s AGI or another false summit, the scale of what we’re building is hard to ignore. There are only a few ways this plays out. 1. We scale current techniques to AGI. The compute, energy, and coordination…
When Software Starts To Listen
Most software today is basically deaf. You poke at it, and if you’re lucky, it does what you want. But it doesn’t listen. Not really. That’s about to change. Say your product’s ad campaign just blew up. The VP wants a buy‑3‑get‑1‑free promotion…
Prompt Engineering Is the New Assembly Language
There’s a belief circulating in AI circles right now that a cleverly written prompt is proprietary gold. That if you can coax the right output from a model, you’ve created something defensible. I get the instinct. When something works, and nobody…