HNHacker News
TopNewBestAskShowJobs

MikahDang

12 karma · joined October 2, 2021

submissionscomments
MikahDang··on GPT-4.5 or GPT-5 being tested on LMSYS?
I FEEL THE AGI I LOVE YOU ALL. - gpt-2 chatbot
MikahDang··on Tell HN: Gpt2-chatbot is a mysterious and surprisngly strong LLM
I FEEL THE AGI
MikahDang··on Show HN: Prompt Engineering Made Easy
Thank
MikahDang··on Show HN: Prompt Engineering Made Easy
Thank!
MikahDang··on Show HN: Prompt Engineering Made Easy
We would check this soon. Thank you for your feedback.
MikahDang··on Show HN: Prompt Engineering Made Easy
I think that is true. And I also think the future would be automated by the algorithm but the human will still be a significant part in deciding the outputs. Humans cannot be replaced 100% unless big corps create something truly AGI.
MikahDang··on Show HN: Prompt Engineering Made Easy
Thank you for your reply. Could you give us more details on that idea?
MikahDang··on Show HN: Prompt Engineering Made Easy
Thank you.
MikahDang··on Show HN: Prompt Engineering Made Easy
This is a great question. Actually, I have two opinions about this: - It is not economically useful for foundational model providers to build this, or at least integrate it with their products, because it will cost them double. They would prefer RLHF and something intrinsic to their models. - Our dataset is proprietary. We have to collect and write a huge number of prompts to fine-tune it well. And our model is not 100% LLM, we use a version of the evolutionary algorithm to control the quality.

I would say we have a tiny moat of data and algorithm. But at the end of the day, it is about delivering something people find useful. If we could be replaced, let it be. But it works for now.

MikahDang··on Show HN: Prompt Engineering Made Easy
Thank you for trying. Yes, this is AI-generated. We fine-tuned a special LLM with a huge dataset of prompts with a Monte Carlo algorithm to explore the solution space. We have evaluated every single prompt in our datasets before fine-tuning them with LLM metrics.