All tags
Topic: "alignment-faking"
not much happened today
qwen-o1 qvq claude-3.5-sonnet gpt-4o o3 o3-mini alibaba openai mit idsia llamaindex ollama vision benchmarking llm-calibration intentionality alignment-faking deliberative-alignment artificial-life gdpr-compliance contract-review-agent app-creation synthetic-data post-transformers smol-models agents bret-taylor
The Qwen team launched QVQ, a vision-enabled version of their experimental QwQ o1 clone, benchmarking comparably to Claude 3.5 Sonnet. Discussions include Bret Taylor's insights on autonomous software development distinct from the Copilot era. The Latent Space LIVE! talks cover highlights of 2024 AI startups, vision, open models, post-transformers, synthetic data, smol models, and agents. Twitter recaps by Claude 3.5 Sonnet highlight proposals for benchmarks measuring LLM calibration and falsehood confidence, with QVQ outperforming GPT-4o and Claude Sonnet 3.5. AI alignment debates focus on intentionality and critiques of alignment faking in models like Claude. Updates from OpenAI include new o3 and o3-mini models and a deliberative alignment strategy. The ASAL project is a collaboration between MIT, OpenAI, and Swiss AI Lab IDSIA to automate artificial life discovery. Personal stories reveal frustrations with USCIS green card denials despite high qualifications. New tools like GeminiCoder enable rapid app creation, and a contract review agent using Reflex and Llama Index checks GDPR compliance. Holiday greetings and memes were also shared.