Giving LLMs a personality is just good engineering(seangoedecke.com)

23 points by dboon 7 months ago | 14 comments

Should LLMs just treat text content as an image?(seangoedecke.com)

159 points by ingve 1 year ago | 94 comments

Two different tricks for fast LLM inference(seangoedecke.com)

177 points by swah 8 months ago | 65 comments

OpenAI's new open-source model is basically Phi-5(seangoedecke.com)

372 points by emschwartz 1 year ago | 200 comments

Sean Goedecke's blog post arguing that OpenAI's open-weight gpt-oss models resemble Microsoft's Phi series, strong on benchmarks but weak on out-of-domain knowledge.

Patience too cheap to meter(seangoedecke.com)

48 points by swah 1 year ago | 17 comments

Patterns for building LLM-based systems and products(eugeneyan.com)

372 points by 7d7n 3 years ago | 49 comments

Eugene Yan's long-form blog post describing seven practical patterns, such as evals, RAG, and fine-tuning, for integrating large language models into systems and products.