GPT 4

1. 79% on LongMemEval: How We Beat Full-Context GPT-4 with a Local SQLite Database (medium.com via hn)

   +2 2w gpt-4

   A benchmark result that changes what we thought was possible for local persistent agent vector memory 9 min read 1 hour ago Press enter or click to view image in full size We ran VEKTOR Slipstream against LongMemEval this week and got a re…

2. Tweaking GPU Clock Frequency Cuts LLM Training Energy (spectrum.ieee.org via hn)

   +2 2w gpt-4openai

   OpenAI’s fourth large language model (LLM), GPT-4, took an estimated 50 Gigawatt-hours to train, or the equivalent of 5,000 American homes‘ yearly power consumption. That was in 2023.

3. Ask HN: Why won't you be replaced by AI? (news.ycombinator.com)

   +511 2w gpt-4mythosanthropic

   AI models are rapidly getting better. The general public still hasn't seen the capabilities of Anthropic's Mythos model, which is already 4 months old at this point.

4. What Are Tokens in LLMs? (bearisland.dev via hn)

   +3 2w gpt-4

   Ask GPT-4 how many r’s are in “strawberry” and it will confidently say two. The right answer is three.

← all threads