Viewing profile — madhatter999

I agree. The Fable fiasco was the first yikes moment in my relationship with Anthropic and based on what I'm reading, this is valid for many others. Sonnet 5 isn't helping their ca…

To add to this, one can’t ignore the relationship between signal and receiver. I’d imagine most people on HN have enough pre-LLM reading experience to have a decent sense of what w…

Plus somebody will create an AI-powered program to take in text and have it “perform” the writing process with keystrokes and mouse movements and all that.

It’s kind of confusing but the comparison is not with input photos to the left, it is with reference photos to the right

Thanks for the clarification. I did look at it pretty quickly initially. Students might be over-relying on GPTs, which means less studying, which means less useful retention in the…

Relying on GPT while solving the problems must be inflating the grades (my use of the word inflate is intentional, because the evaluation does not represent the true knowledge of t…

From the abstract: “Consistent with prior work, our results show that access to GPT-4 significantly improves performance (48% improvement for GPT Base and 127% for GPT Tutor). Howe…

Also take into consideration the speed of evolution. LLM training might be much faster because a lot of competition power is used for its training. Maybe if it was the same speed a…

This[0] study might have some pointers in the discussion section. [0] Grateful students are motivated, engaged, and successful in school: Cross-sectional, longitudinal, and experim…

I didn't know notebooklm had that feature embedded. Thanks for sharing!

Thank you for the pointer! What makes LlamaIndex different than other similar tools in your opinion?

Thank you for the answer! Wouldn't it make sense to compare the potential answers to the questions to the parts of the documents?

Dear HN, I am trying to do some semantic search in a given corpus of PDF documents based on a question as input. My goal is to find the relevant parts from the PDF that best answer…

Very promising tool based on a couple of questions I asked it! How did the cleaning of documents look like?

Absurdity aside, I set a reminder for any trial end, preferably a couple of days before.

Upward doesn’t have to be linear

A minute? It’s eternity in my thumb managed universe.

Now if you were drunk while playing Need for Speed, that wouldn’t be a problem because there is no “real” humans being endangered by your actions.

Pedantically explained.

You, I and everyone else and when enough people operate on highly likely’s, we stop being as interested in the why. For good reason, too. People like Musk will expect us to look at…

Life is not just this or that. Life is also highly likely this or likely that. When you have a track record and make a lot of people have this image about you, many people will ope…

Good idea. Why not cache the examples?

First question that came to mind was when will Google kill this service and when will I have to export all my content?

Look how awesome and important we are in AI, and now we are together