The purpose of the looking at the future...is to disturb the present!

Gaston Berger (1896-1960), francuski futurolog

AI LLM Improvement Rate Slows on Pre-training but Memory and Actions Make AI More Useful

Super Venture Capitalists Bill Gurley and Brad Gerstner analyze the future of AI. The rate of improvement of large language models is slowing for pre-training. However, it is still improving and AI intelligence is improving with post-training and test time training. OpenAI and Microsoft announced a major AI advancement for 2025, featuring models with infinite ...

Read more


Link :
https://www.nextbigfuture.com/2024/11/ai-llm-improvement-rate-slows-on-pre-training-but-memory-and-actions-make-ai-more-useful.html