Founder vibe-codes an FPGA into running LLM inference with coding agents

ycombinator · x · 2026-11-20

Ankit Gupta (YC) recounts vibe-coding an FPGA to run LLM inference end to end. With little prior FPGA experience, he leaned on coding agents to write low-level C++/Verilog and verify waveforms—and found the models surprisingly capable at hardware programming. His takeaway: agents let engineers enter entirely new domains when given a large token budget and an interesting problem.

Original post →

More from coding & agent

coding & agent channel →