Bridgewater and Thinking Machines Lab Achieve High AI News Filtering Accuracy

@TheRundownAI· July 2, 2026 View original

Summary

Bridgewater and Mira Murati's Thinking Machines Lab collaborated to use AI for filtering financial news, achieving 84.7% accuracy after fine-tuning. This significantly improved upon frontier models and expert-crafted prompts, while also reducing costs.

Mira Murati's Thinking Machines Lab partnered with Bridgewater, the world's largest hedge fund, to explore AI's capability in a crucial investment task: identifying relevant news for financial analysts. Initial tests with leading frontier AI models like GPT, Claude, and Gemini showed accuracy around 50% in filtering tasks. Even with expert-designed prompts, accuracy only reached the mid-70s, falling short of the 80% threshold Bridgewater's investors required for daily operational trust. The breakthrough came through fine-tuning. Utilizing TML's Tinker API, Bridgewater trained an open-weight model using their experts' actual judgment calls on news relevance. This specialized training boosted accuracy to 84.7%, reducing errors by nearly 30% compared to the best frontier model. Furthermore, the fine-tuned solution offered a 13.8x lower cost per task, demonstrating the significant efficiency gains possible with tailored AI applications.

Why it matters

This collaboration demonstrates that fine-tuning open-weight AI models with proprietary expert data can yield superior accuracy and cost efficiency compared to off-the-shelf frontier models for specific business tasks. Professionals can learn that custom AI solutions, even for seemingly simple tasks, can deliver significant operational advantages.

How to implement this in your domain

  1. 1Identify a specific, high-volume task currently performed by experts that involves data filtering or decision-making.
  2. 2Benchmark current AI model performance (e.g., GPT, Claude) on this task using your internal data and expert-defined criteria.
  3. 3Collect a dataset of expert judgments on the task to use for fine-tuning an open-weight model.
  4. 4Develop or utilize a fine-tuning pipeline to train a specialized model on your expert data.
  5. 5Evaluate the fine-tuned model's accuracy and cost-effectiveness against both human performance and frontier models.

Who benefits

BFSIMediaConsultingLegalHealthcare

Key takeaways

  • Fine-tuning open-weight AI models with expert data significantly outperforms generic frontier models for specialized tasks.
  • Achieving high accuracy in AI-driven decision support requires domain-specific training and expert input.
  • Custom AI solutions can lead to substantial cost reductions per task compared to using large, general-purpose models.
  • Even seemingly basic tasks like news filtering can benefit immensely from tailored AI applications.

Original post by @TheRundownAI

"Mira Murati's Thinking Machines Lab and Bridgewater, the world's largest hedge fund, published joint results on using AI for a basic but important task in investing: Deciding which news deserves an analyst's attention. First, Bridgewater tried the frontier models. GPT, Claude, an…"

View on X
Bridgewater and Thinking Machines Lab Achieve High AI News Filtering Accuracy

Originally posted by @TheRundownAI on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses