Posts by Tags

Algorithmic Collective Action

Alignment

Benchmarking

Efficient computation of MMLU-scores

less than 1 minute read

Published:

Relinking the blog post I wrote at Vijil where we enabled scoring against benchmarks (MMLU) by using the tinyBenchmark methodology. Combined with Vijil engine, we can much more quickly get an accurate estimate all kinds of metrics one might want to evaluate.

Data Leverage

Economics

Fair Pricing

Incentive Mismatch

Instacart

Internship

Efficient computation of MMLU-scores

less than 1 minute read

Published:

Relinking the blog post I wrote at Vijil where we enabled scoring against benchmarks (MMLU) by using the tinyBenchmark methodology. Combined with Vijil engine, we can much more quickly get an accurate estimate all kinds of metrics one might want to evaluate.

LLM

Efficient computation of MMLU-scores

less than 1 minute read

Published:

Relinking the blog post I wrote at Vijil where we enabled scoring against benchmarks (MMLU) by using the tinyBenchmark methodology. Combined with Vijil engine, we can much more quickly get an accurate estimate all kinds of metrics one might want to evaluate.

LLM alignment

Machine Learning

Market Mechnaisms

Research

Efficient computation of MMLU-scores

less than 1 minute read

Published:

Relinking the blog post I wrote at Vijil where we enabled scoring against benchmarks (MMLU) by using the tinyBenchmark methodology. Combined with Vijil engine, we can much more quickly get an accurate estimate all kinds of metrics one might want to evaluate.

Vijil

Efficient computation of MMLU-scores

less than 1 minute read

Published:

Relinking the blog post I wrote at Vijil where we enabled scoring against benchmarks (MMLU) by using the tinyBenchmark methodology. Combined with Vijil engine, we can much more quickly get an accurate estimate all kinds of metrics one might want to evaluate.