HN Update

State of the Art of Coding Models,
According to Hacker News Commenters

The space of AI-assisted coding is evolving rapidly. This is an attempt at staying up to date with the latest developments, by capturing popularity and user sentiment of coding models from Hacker News comments. Updated daily.

Each day, the pipeline

  1. Gets the 200 most popular posts in a 24h window from the Hacker News API.
  2. Prompts an LLM to select those posts whose titles are about LLMs or coding in general (max. 50), as we expect more relevant discussions in those posts (assumption on my part).
  3. For each post, sends the title and comments to Gemini and asks it to identify models from the OpenRouter model list and rate the sentiment towards each mentioned model per comment.

I wanted the ability to audit the process and the results, for debugging and for occasional sanity checks of the model outputs. So the results are logged to a Google Sheet, where you can see the comment IDs that mention specific models and the sentiment that the model determined for that comment and model.

You can open a comment by appending the comment ID to https://news.ycombinator.com/item?id=.

The chart below is embedded from Google Sheets. If it doesn't load for you, you should be able to see the same chart by opening the Sheet directly.

Top 10 Model Popularity

Total mentions and user sentiment of specific models, 10 days trailing aggregate (… to …).

Google Sheets link with granular results.

Home

LingoLingo - Learn languages with YouTube!