Stories by fzliu

HDBSCAN

voyage-3-large

Evaluating Code Embedding Models

Salesforce AI Research Falsely Claims #1 on Leaderboard

Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search

Check twice, cut once with LLM search relevance eval

Coping with dumb LLMs using classic ML

General-Purpose vs. Domain-Specific Embedding Models

Evaluating Code Embedding Models

voyage-3-large

Salesforce AI Research Falsely Claims #1 on Leaderboard

Micropayments

Evaluating Embedding Models for Code

voyage-3-large

Decisionator

The evolution of incident response at Podia

General-Purpose vs. Domain-Specific Embedding Models

Long Paths on Windows

Evaluating Code Embedding Models

voyage-3-large

1
2
3
4
5
6
7
8
9
10