On this day: Mar 4
3 records from this date, 2022 to 2024, gathered year by year — the most recent year first.
2024
2 years ago · 2 recordsSarathi-ServeMicrosoft Research India (Agrawal et al.)
Solved the problem of long prompts stalling decode; 2.6–5.6× the serving capacity of vLLM
Anthropic announces the Claude 3 family (Haiku, Sonnet, Opus)Anthropic
Opus and Sonnet available on launch day in claude.ai and the Claude API, generally available in 159 countries, with Haiku to follow. Per 1M tokens: Opus $15/$75, Sonnet $3/$15, Haiku $0.25/$1.25; assessed at ASL-2 under
2022
4 years ago · 1 recordOpenAI publishes the InstructGPT paper on arXivOpenAI (Ouyang et al.)
Showed that outputs of the 1.3B model were preferred to those of the 175B GPT-3, establishing RLHF as the standard procedure for alignment
Prompt EngineeringPaper