Metaculus / Metaculus/metaculus

Upgrade existing LLM models

Open
#4,379 1 comment 0 reactions 1 assignee View on GitHub

@hlbmtc is already working on this.

Since Feb 17, 2026.

Medium Priority Stale
Dominant language
TypeScript
Stars
113
Forks
34
Avg merge
16h 34m
Merged PRs (30d)
30

Description

Currently, we’re using gpt-4o in many places (spam checks, LLM suggestions, etc.), which is a bit outdated. We should evaluate newer OpenAI models and other providers (e.g., Gemini 3 Flash), compare speed and performance, and consider migrating the app.

We should also look into whether it makes sense to upgrade the embeddings model.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.