‘Code’
more accurate code retrieval with lower dimensional, quantized embeddings – Voyage AI
TL;DR – Introducing voyage-code-3, our next-generation embedding model optimized for code retrieval. It outperforms OpenAI-v3-large and CodeSage-large by an average…
Mistral’s new Codestral code completion model races up third-party charts
The newest version of Mistral’s code generation model Codestral aims to be more efficient and generate code twice as fast.Read…
Self-invoking code benchmarks help you decide which LLMs to use for your programming tasks
LLMs are good at coding simple functions. But how good are they at calling their own functions to solve complex…
The day I taught AI to read code like a Senior Developer
A messy experiment that changed how we think about AI code analysis Last week, I watched our AI choke on…
Advent of Code 2024 in pure SQL
On a whim I decided to do this years advent of code in pure SQL. That was an interesting experience…
Ask HN: How do you maintain personal annotations for code you don’t control?
I spend significant time reading and understanding codebases that I don’t control (open source libraries, internal legacy systems, etc.). As…
If ChatGPT produces AI-generated code for your app, who does it really belong to?
monsitj/Getty Images In one of my earlier AI and coding articles, where I looked at how ChatGPT can rewrite and improve…
The code whisperer: How Anthropic’s Claude is changing the game for software developers
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More The…
GitHub makes AI Copilot free for VS Code developers — with limits
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Microsoft…
Google upgrades its programming agent Code Assist with Gemini 2.0, adds source integrations
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More On…