Can LLMs find bugs in large Python codebases? 2 years ago
I'm a bit disappointed about the results on Llama3, I was hoping it would be much better than GPT3.5 Are you planning to do other LLM coding benchmarks in the future?
HN user
mbuleandra
1 karma
YC Badge: 0xd3bb290e9b6a97e690b49b7f9400d47f9df95e6f
Posts0
Comments2
No posts found.
SEEKING WORK | Los Angeles, CA | Remote
● Previously SDE/TechLead at Anduril, Square, Microsoft
● 15+ years of experience in Software Development
---
I have extensive experience with both GCP and AWS, building high-performance micro-services, Big Data / ETL, MLOps, DevOps.
Relevant technologies: Go, gRPC, Rest APIs, GraphQL, Docker, Kubernetes, Python, Spark, Kafka, Databricks, SQL, BigQuery, TypeScript, Node.js and many more.
---
LinkedIn: https://www.linkedin.com/in/mariusbuleandra
Email: mbuleandra.ai@gmail.com
---
Please drop me a line and include “Hacker News” in the subject.