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.
More from coding & agent
- CapCut plugin connects ChatGPT to auto-cut gameplay highlights, then human picks the payoff — iamfakhrealam · 2026-11-21
- Dev wires a Runway-generated avatar into Nous Research's Hermes Agent, bashing boring agent UIs — alexcovo_eth · 2026-11-21
- Lean compiles, but the natural-language proof is still wrong — jasondeanlee · 2026-11-21
- DeepMind demos ski simulator built by Gemini 4 Neon from real Mont Blanc terrain — GoogleDeepMind · 2026-11-21
- pstack v0.15.46 trims skills, adds Gemini as panel reviewer; pinning question raised — petrusenko_max · 2026-11-21
- Hamel Husain on evals: a good process beats good tools — HamelHusain · 2026-11-21