Top all-time · #6428
Jason Liu
Personal blog · jxnl.github.io/blog/writingaiprogramming
Jason Liu's personal blog at jxnl.github.io covers ai and programming. Since 2023, 12 different Hacker News readers have linked it 23 times, most often “Rag is more than just embedding search”. No feed was found, so read it on the site itself.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
HN readers link Jason Liu's blog for writing on LLM tooling, such as RAG retrieval and structured outputs, and point to his Instructor library docs. Personal essays also come up.
- Recommended for · 1 comments
- One commenter calls a linked article on RAG query handling and structured metadata filtering a good article.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Professional business card for Jason Liu, Vice President of Consulting Services at FIVESIXSEVEN LLC.
Most-linked posts?
- Rag is more than just embedding search2 people · 2 mentions · first linked 2023-09-21
- Stop Using LGTM as a Metric2 people · 2 mentions · first linked 2024-02-06
- Good LLM Validation Is Just Good Validation2 people · 2 mentions · first linked 2023-10-27
What Hacker News says?
Good stuff. How does this compare to Instructor? I’ve been using this extensively https://jxnl.github.io/instructor/
Comment linking /instructor/
on “Show HN: Fructose – LLM calls as strongly typed functions”Submitted Advice to young people, the lies I tell myself as a story · 148 points
HN discussionHey, I've been thinking about what you said, and I believe it has helped me gain some clarity about myself. I have written a response specifically for you, and I hope that as someone who is in touch with reality, you can sense the sincerity in my words. https://jxnl.github.io/blog/writing/2024/01/09/self-loathing...
Comment linking /blog/writing/2024/01/09/self-loathing/
on “Advice to young people, the lies I tell myself”Submitted Smarter Summaries with Finetuning GPT-3.5 and Chain of Density as a story · 6 points
HN discussionI wonder, where did you get all that about privilege, upper-middle class, gated community, and private schools? Do you know the author personally? According to his bio at https://jxnl.github.io/blog/writing/2024/01/01/whoami/ > I was born in a village in China. My parents were the children of rural farmers who grew up during the Cultural Revolution. They were the first generation of their family to read and write, a…
Comment linking /blog/writing/2024/01/01/whoami/
on “Advice to young people, the lies I tell myself”Submitted What I Learned from Trying as a story · 4 points
HN discussioninteresting, thanks for sharing! Maybe check out if instructor helps https://jxnl.github.io/instructor/examples/knowledge_graph/ What do you use for the UI?
Comment linking /instructor/examples/knowledge_graph/
on “Show HN: Generate Knowledge Graphs with LLMs”Submitted What I Learned earning $40k/month from Indie Consulting as a story · 3 points
HN discussion>I asked it a few simple fact based questions, such as who our CEO is. It answered with our previous CEO based on an old press release. this is the problem with basic RAG implementations that most products are currently using, simple vector search isn't able to handle queries like this. The solution is enhancing the base query and also using structured data to filter on metadata here's a good article covering some s…
Comment linking /instructor/blog/2023/09/17/rag-is-more-than-just-embedding-search/
on “First look at Microsoft 365 Copilot”Submitted Good LLM Validation Is Just Good Validation as a story · 3 points
HN discussionSubmitted Distilling Python Functions into an LLM Finetune as a story · 3 points
HN discussionSubmitted Structured Data for Open-Source LLMs as a story · 2 points
HN discussionSubmitted Advice to Young People, the Lies I Tell Myself as a story · 2 points
HN discussionSubmitted Questions AI Engineers need to ask themselves as a story · 2 points
HN discussionSubmitted Streaming Structured Outputs with LLMs as a story · 2 points
HN discussionSubmitted Python caching decorators in three levels as a story · 2 points
HN discussionSubmitted Introduction to async batching using `asyncio` and `OpenAI` as a story · 2 points
HN discussionSubmitted Rag is more than just embedding search as a story · 2 points
HN discussionSubmitted Stop Using LGTM Few for RAG as a story · 1 points
HN discussionSubmitted How to Ship an AI Application MVP as a story · 1 points
HN discussionSubmitted Seamless Support with Langsmith as a story · 1 points
HN discussionSubmitted Stop Using LGTM as a Metric as a story · 1 points
HN discussionSubmitted Good LLM Validation Is Just Good Validation as a story · 1 points
HN discussion
