k2xl

I've done something similar for learning about a controversial topic. I ask it to act as if it is called Bob is a well informed supporter of one side (like Ukraine) and then act as if it is something named Alice who is a well informed supporter of another side (Russia) and they have to debate each other over a few prompts with a moderator named 'Sue'

Then after a few rounds of the debate where Sue asks a bunch of questions, I ask it to go to the judges - Mark, Phil, Sarah (and I add a few personalities to each of them... Sometimes I pretend they are famous moral philosophers) and then I have them each come up with a rubric and decide who is the winner.

Really fun, and helps me understand different sides of issues.

I think i mentioned this in my original reply- the app was already built and too integrated with supabase, it is hard to leave

I've been a lukewarm user of Supabase for my side projects. Unfortunately the amount of work to get off of it has been too high for me to leave.

The major issue is - cost. It is way more expensive than I realized as they have so many little ways they charge you. It's almost like death by thousands of paper cuts. My bill for my app with just a few thousand users was $70 last month.

I do like the tooling and all, but the pricing has been very confusing.

There is a similar issue with image and video generation. Asking the AI to "Generate an image of a man holding a pencil with his left hand" or "Generate a clock showing the time 5 minutes past 6 o'clock" often fail due to so many images in the training set being similar (almost all clock images on show 10:10 (https://generativeai.pub/in-the-ai-art-world-the-time-is-alm...)

I can’t use their video gen model veo2 since there is a waitlist… hard to tell if they are winning in video when they haven’t scaled that product.

He isnt saying texas is less bias, but from public perception perspective, california is biased.

Something not mentioned is AI generated music. Suno's development this year is impressive. Unclear what this will mean for music artists over next few years.

What model does it use under the hood?

How much context window does it load when it is solving tasks?

How does it determine which files to load into context?

It says at the top $500 per month

This is impressive, but why are they all looking still like a video game? Could they have this render movie scenes with realistic looking humans? I wonder if it is due to the training set they use being mostly video games?

Not to dispute the main point you are making, but that's assuming 360K salary. OpenAI engineers make significantly more than that.

Trying to find a pricing page.. Anyone find one?

The amount of data that would be required for a lookup table for all best moves for every board configuration would be infeasible.

They have managed to create one for 7 pieces. Last update on trying to get to 8 piece database: https://www.chess.com/blog/Rocky64/eight-piece-tablebases-a-...

Could o1 have helped the hunters finally reach it?

Pricing page updated for O1 API costs.

https://openai.com/api/pricing/

$15.00 / 1M input tokens $60.00 / 1M output tokens

For o1 preview

Approx 3x the price of gpt4o.

o1-mini $3.00 / 1M input tokens $12.00 / 1M output tokens

About 60% of the cost of gpt4o. Much more expensive than gpt4o-mini.

Curious on the performance/tokens per second for these new massive models.

Been hesitant to get due to battery life. My fitbit lasts for days on one charge. Is there ways to configure the watch settings to extend the battery life for more than a day?

that would be great... i'm curious on the cost per million token as it compares to gpt-4o-mini

Nice - btw curious how much it costs to run Llama on this type of side project? I can imagine the cost goes to some reasonable amount when things like this get shared on HN. Does Fly.io give a flat price to use their inference? Curious how it works

This is great - Though I am confused on two things:

1. How is it possible that GPT-4o mini outperforms 3.5 turbo but 3.5 turbo is more expensive? Like why would someone use a worse model and pay more?

2. Why is the GPT4o vision and GPT4o-mini vision cost the same?

Shameless plug for a side project i have been working on for a few years, but if you like Baba is You you may enjoy Pathology or Sokopath. They can be played on my site Thinky.gg (https://thinky.gg)

Theres a pretty active community on Thinky publishing block pushing levels every day. Levels range from Kindergarten to Super Grandmaster in difficulty. Also features a level editor where you can publish custom levels to the world.

Would be great if it had Zwave and Zigbee support... Would love this for home automation use cases

Lot of investment in new data centers getting built from big tech companies. I imagine they want to highlight chips that will be ready in time for those new constructions to break ground.

2% conversion for an 8K purchase is actually incredibly high.

Bought in 2018 and v12 has been absolutely amazing. Next version 12.4 will also remove the steering wheel nag.

Would be neat to see this on much older videos (maybe WW2 era) to see how it improves details.

Curious on if others have switched from vscode to Zed and can share their experiences

Turbo tax comes to mind

Shameless plug, but if you are interested in Sokoban type games check out https://thinky.gg . Features a fun Sokoban variant (called Sokopath) as well as another NP hard variant called Pathology (goal is to get from point A to point B in the shortest amount of steps).

Many in the community have tried to create various solvers and things get very hard once the grid gets to be over 5x5. However, some interesting levels with very high maximum step counts have been discovered by the thinky communnity (via simulated annealing)

Deflation will be stronger than expected and will actually be a problem (fed will be too late in reducing interest rates)

This kind of thinking reminds me of Loose Change 9/11 conspiracy about how 9/11 was an inside job. Do you agree that there is parallels in the conspiracy theories?

Why do you think there is a good chance?