llm
Design by Patrick Lauke I use LLM’s I use LLM’s to better understand how they work and understand their limitations. I use LLM’s to create software I cannot I u…
Making a mockery of alignment
(摘要暂无, 请查看原文)
You’re deploying a model on a system. It starts up, prompts are getting responses. Now the hard question: Is this fast? Your instincts might lead you to send...
Tips and tricks on writing robust evals for coding agents that test apps whose code we've never seen: different UI/UX contract strategies, UI mutation testing, …
In today’s issue, we’re featuring an excerpt that introduces the Three Gulfs of LLM Application Development.
(摘要暂无, 请查看原文)
(摘要暂无, 请查看原文)
LLM-based chatbots’ capabilities have been advancing every month. These improvements are mostly measured by benchmarks like MMLU, HumanEval, and MATH (e.g. sonn…





