79% on LongMemEval: How We Beat Full-Context GPT-4 with a Local SQLite Database (medium.com via hn) gpt-4 22w
event
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…
-
Tweaking GPU Clock Frequency Cuts LLM Training Energy (spectrum.ieee.org via hn) gpt-4openai 22w
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.
-
Ask HN: Why won't you be replaced by AI? (news.ycombinator.com) gpt-4mythosanthropic 22w
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.
-
What Are Tokens in LLMs? (bearisland.dev via hn) gpt-4 23w
Ask GPT-4 how many r’s are in “strawberry” and it will confidently say two. The right answer is three.