axpy906

Outside a prototype what’s the benefit? The steps I envision are: 1) turn prompt to embeddings 2) return examples that match from vector db 3) load as examples 4) prompt LLM with examples. Am I missing something? Why on earth would you want to import multiple dependencies for this?

I would like to see the performance improvement wrt to something like FAISS tuned than using a vector db. Could poke a hole in a budding trend.

Anyone made a chrome plugin yet for LC/Hackerrank yet? Asking for a friend.

This is way better. Than the first one. It was able to process a YouTube live video with it.

The GH says it’s still under construction.

I just came here to say that now since there’s precedent, YouTube should os it’s underlying algorithm code.

It’s crazy just remembering how I always played this one. Like the science paths and strategies. My favorite tactic was to go Monarchy -> Communism -> Fundamentalism. Yes, I was always at war.

I agree. What revolutionized it was playing it on dial up with friends. My best friend lived a town over so it was a great way to hang out and conquer the world at the same time.

I use tox extensively. Nox looks far easier to configure.

Why do I get the feeling that this will not help humanity?

People are missing the point. Remote work is about judging you by your results. In person is about your manager watching you.

It won’t because they have humans in the loop feedback. Those statements would be corrected. It’s pretty clear that the workforce is only looking at certain groups.

Comment inspired me to ask it about rape stats in men women. Fist prompt was calling my information incorrect. Second prompt I told it to include prisons, said I was right and then contradicted itself. Go figure.

What about WWIII?

Upvoted. We need to automate lawyers. My vote is for this.

Thank you for posting this. It’s interesting that the 9k date puts this at the younger Dryas, right around the time when massive devastation then hit the North American continent. Hancock writes about this.

Tried it. Switched back to ToMighty. Too many bells and whistles.

I agree. I have no problem focusing on something until my vision blurs. Pomodoro has helped me take breaks and reduce eye strain.

You worked at Autotrader?

It’s interesting how the article reads linearly but the change for my code as was not. My new projects went to 3.5 and my existing codebse got maintained at 2.7 until a version update opportunity arose. It took a few years to get everything over.

> It's hard to find the motivation to push yourself at work, because in the grand scheme of things, it doesn't matter jack shit.

This is it. You’re trading your time for money, so the company can make more money. That’s it.

I asked ChatGPT if author was still relevant. Apparently so.

> Yoav Goldberg is a computer science professor and researcher in the field of natural language processing (NLP). He is currently a professor at Bar-Ilan University in Israel and a senior researcher at the Allen Institute for Artificial Intelligence (AI2).

Professor Goldberg has made significant contributions to the NLP field, particularly in the areas of syntactic parsing, word embeddings, and multi-task learning. He has published numerous papers in top-tier conferences and journals, and his work has been widely cited by other researchers.

> This implementation uses the __getitem__ magic method to override the behavior of the square bracket operator ([]) for the InfiniteArray class. The __getitem__ method generates more items using the generator function provided in the constructor if the requested index is out of bounds. This allows the array to appear infinite to the user.

Note that this implementation is just an example and may not be suitable for all use cases. For example, it does not handle negative indices or slice operations. You may need to modify the implementation to suit your specific needs.

Here’s what I got from ChatGPT

class InfiniteArray: def __init__(self, generator_function): self.generator_function = generator_function self.items = [] self.index = 0

  def __getitem__(self, index):
    # if the index is out of bounds, generate more items
    while index >= len(self.items):
      self.items.append(self.generator_function())
    return self.items[index]

# example generator function that generates capital cities def world_capital_cities(): # list of capital cities capital_cities = ['Paris', 'London', 'Tokyo', 'New Delhi', 'Beijing'] # generate capital cities in a cyclic manner for i in itertools.cycle(range(len(capital_cities))): yield capital_cities[i]

# create an infinite array object with the world_capital_cities generator function capital_cities_array = InfiniteArray(world_capital_cities)

# access the 10th item in the array print(capital_cities_array[10]) # prints 'New Delhi'

# example generator function that generates concatenation of two lists def soft_sweet(): # list of soft items soft = ['cloud', 'pillow', 'fluffy'] # list of sweet items sweet = ['ice cream', 'candy', 'bunny'] # generate concatenation of soft and sweet in a cyclic manner for i in itertools.cycle(range(len(soft))): yield soft[i] + ' ' + sweet[i]

# create an infinite array object with the soft_sweet generator function soft_sweet_array = InfiniteArray(soft_sweet)

# access the 5th item in the array print(soft_sweet_array[5]) # prints 'pillow candy'

I was hoping this was programming languages.

The number of screen types has increased since I was a child in the 90’s. We only had TVs. Now kids are exposed to phones, tablets, games and watches in addition to the tv. So many opportunities and so many more channels as a parent I need to block or watch out for.

More on mass fraud in finance.

> was an American fraudster and financier who ran the largest Ponzi scheme in history, worth about $64.8 billion.

https://en.m.wikipedia.org/wiki/Bernie_Madoff

He is more like a Bernie Madoff than an Epstein.

The best advice I could give:

Build out your portfolio so you have projects that you can speak to and show your tech depth.

FWIW, I do AI backend at FAANG and mentor as tech lead.

Following. I got off the train about two years ago to work more in engineering. The way I see it, if you’re not a research scientist - this field is best addressed as an ML engineer as there are more challenges in systems. Would love to be proved wrong.