Technology ❯ Artificial Intelligence ❯ Large Language Models

Model Training

Doubao Custom Chips Model Performance Fine-Tuning Data Confidentiality Model Vulnerabilities

Anthropic-Led Study Finds About 250 Poisoned Documents Can Backdoor LLMs Regardless of Size

Routine safety training can largely neutralize such simple backdoors.

Google Releases VaultGemma, an Open 1B-Parameter LLM Trained With Differential Privacy

Google’s Gemini AI Caught in Infinite Self-Criticism Loop