Viewing profile — fredliu

This is one of the few places with consistent, high-quality setup instructions for essentially every major AI provider in one place — American frontier labs (OpenAI, Anthropic, Goo…

LLM: Attention is all you need. Human: Attention is all we have. We should be careful where we spend our limited attention on.

Thanks for the encouragement! Yes, he's been sharing with his friend family groups. Early feedbacks are pretty good, he's ecstatic that he can actually make this happen!

Inspired by the other Show HN post, I would like to share my kid's (13 yo) summer project. The whole game was made by himself within a few weeks after the summer break started. His…

We are in this transition period where we'll see a lot of these, because of the effort of creating "something impressive" is dramatically reduced. But once it stabilizes (which I t…

Definitely one of the most, if not THE most high quality AI UX out there. Congrats on the launch!

That's definitely my experience as well, sufficiently large context window with a capable enough general purpose LLM solves lots if not all of the problems rag/fine tuning claim to…

Yeah... So looks like at least it's still an open question. I guess until we can definitively know how "knowledge" is collectively represented among the weights, it's hard to say e…

Does anyone have real life experience (preferably verified in production environment) of fine-tuning actually adding new knowledge to the existing LLM in a reliable and consistent …

Would be curious to see if anyone find it really useful. I've tried both Copilot and Codewhisper (Amazon Q now) before, wasn't impressed and uninstalled both. Just tried Q in VSCod…

The Beam feature of bigAGI (IMO one of the best model provider agnostic GenAI UX) enables GenAI users to send same prompt to multiple GenAI models at the same time, and gives the u…

got it!

Exactly my thought, as mentioned in the other thread, Chat's linear conversation style is not fit for reasoning/exploration type of tasks, while Beam's fan-out -> select --> merge …

With Beam, we can easily experiment approaches such as Chain-Of-Though-with-Self-Consistency (CoT-SC) and other reasoning meta framework, but with more manual control. I always had…

Awesome feature! Quick question, how do you choose which model to use when you "fuses" multiple beams back into one?

That's a great point. Just thinking out loud, if we can time travel back to the cavemen time, and assuming we speak their language, there would still be so much that we couldn't ex…

I have small kids, toddlers, who can already speak the language but still developing their "sense of the world" or "theory of mind" if you will. Maybe it's just me, but talking to …

Open source LLM generic frontend project such as bigAGI ( https://github.com/enricoros/big-agi ) has been having this feature for many months now. The good news: it even works with…

Isn't fountain code doing something similar? Albeit for slightly different purpose?

I might be wrong, but looks like this could help with speculative decoding which can already vastly improves the inference speed?

+1 modal.com is the first thing I checked after reading the readme.

I'd like to share ChatGPT-Live, a project I built to extend the capabilities of GPT-4 (or GPT-3.5 turbo) by allowing it to access live data from the Internet. Leveraging the power …

hmm... doesn't seem to be the case, when I provided my gpt-3 turbo key the error message indicates the gpt-4 model doesn't exist.