Gupta rented an AWS F2 instance, which has an FPGA with 16 GB of HBM, and set out to run DeepGrove's ternary-weight model on it. A cloud agent ran in Conductor for several days while he mostly encouraged it.
In the News: November 20, 2026 (Evening)
Ankit Gupta let coding agents run for days on an AWS FPGA and got a language model 33 times faster, held to a bit-exact reference.
Evening edition
Machine-readable
Download Markdown
Story
Coding agents spend days and $10,000 getting a language model 33x faster on an FPGA
Read story →
OpenComputer
An Apache-2.0, self-hostable coding agent that you assign work by mentioning it in a Slack thread. It runs Claude Code, Codex or OpenCode in sessions isolated with rootless Podman on a single VM, and the result arrives as a pull request. The team's own benchmark of 4 PRs says it opened them with CI green in 56 seconds against 185 for Devin.