The Coding Test Looked Legit. It Was Actually a $10 Million Crypto Trap

North Korea's WaterPlum group stole $10.71M and infected 30,000 devices using fake coding tests. Here's how to spot the attack.
Help Net Security

Reflection’s Beam trails top open models on coding tests but claims lower inference compute

Reflection Beam open-weight model trails top rivals on coding tests but claims 3-4x less inference compute. Weights arrive ...
ZDNet

I tested Meta's Code Llama with 3 AI coding challenges that ChatGPT aced - and it wasn't good

A few weeks ago, Meta CEO Mark Zuckerberg announced via Facebook that his company is open-sourcing its large language model (LLM) Code Llama, which is an artificial intelligence (AI) engine similar to ...
ZDNet

I put GitHub Copilot’s AI to the test – its mixed success at coding baffled me

The thing I find most baffling about the programming tests I’ve been running is that tools based on the same large language model tend to perform quite differently. Also: The best AI for coding in ...
Crypto Briefing

Meta study shows two AI coding agents catch more bugs than one with a bigger budget

Meta research finds two AI coding agents reviewing each other's patches catch more bugs than one agent with a bigger budget.