NBenkovich

↗ HN profile [ 55.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Hi HN, We recently ran an experiment to answer a simple question: Does coordinating multiple AI agents as a team actually help with real software engineering tasks, compared to a single strong agent? To test this, we…

  2. To make AI agents more efficient, we need to build feedback loops with real systems: deployments, logs, configs, environments, dashboards. But this is where things break down. Most modern apps don’t have fine-grained…

  3. When I use AI for coding, I don’t use one model. I use strong reasoning models to understand a codebase or plan changes, then switch to faster and cheaper models for implementation and refactors. In practice this means…

  4. Hi HN, I’m working on AI agents used for software development. These agents automatically spin up short-lived app instances – for example per pull request, per task, or per experiment – each with its own temporary URL.…

  5. I built gh-pr-review, an open-source GitHub CLI (gh) extension that lets AI agents fully operate on GitHub Pull Requests. Repo (try it locally, no signup): https://github.com/agynio/gh-pr-review What you can try right…

  6. GitHub’s official CLI (`gh`) does not provide a built-in way to view or interact with inline pull request review comments or review threads. The available command (`gh pr view --comments`) only shows top-level…