r0b05

Are you saying that Anthropic might be the ones pushing this?

I want to set this up but I'm concerned about the privacy and security risks. On the one hand, person data is flowing through cloud models. Then there's the risks of prompt injection and such.

I thought about running it locally but it gets expensive.

Those that have taken the plunge, how did you make peace with these trade offs?

Cool insight!

I agree with all of this. The brain needs exercise, just like the body.

I have been wondering where this trend started as well. It's geared towards vibe coders who don't need to see a lot of info.

This is one of the biggest issues with hosted models used via subscription. You have no idea what level of quality and accuracy you are consistently getting. That's why it's cheaper - because they can nerf it as they wish and most consumers would be none the wiser.

Elaborate please

> I have a GPU, a cheap Chinese coding plan, and a dream

Right in the feels

NFT moment

Is it easy and advisable to host your own email server on vps?

Is the PPI not too small with the 43"?

I have a 4k 27" which has nice PPI and I was considering this 43" as a replacement but the pixels looked quite prominent in youtube reviews.

It's a good take. I think both trajectories are occurring simultaneously.

OpenAI challenging Google search is a winner takes all situation, not to mention the vast amounts of user data.

On the other hand, us lesser mortals can leverage AI like a commoditized service to build applications with it.

Yes, the privacy is amazing, and there's no rate limiting so you can be as productive as you want. There's also tons of learnings in this exercise. I have just 2x 3090's and I've learnt so much about pcie and hardware that just makes the creative process that more fun.

The next iteration of these tools will likely be more efficient so we should be able to run larger models at a lower cost. For now though, we'll run nvidia-smi and keep an eye on those power figures :)

I think 14 3090's are more than a little power hungry!

What is your estimate for when memory prices will decrease?

I agree that we've seen similar fluctuations in the past and the price of compute trends down in the long-term. This could be a bubble, which it likely is, in which case prices should return to baseline eventually. The political climate is extremely challenging at this time though so things could take longer to stabilize. Do you think we're in this ride for months or years?

I think this is a great take.

Thanks will check out the aula 75

Thanks for the info. A split keyboard sounds awesome.

Touché sir.

Does anyone know which keys/switches out there sound like this one?

It's got a soft cheery non-intrusive sound that I really like compared to the usual louder mechanical keys/switches that I hear in videos.

Glad to see more touchpads. Apple magic trackpad needs some serious competition.

What is the model number and how has the experience been?

I've mostly read that TV's don't make great monitors. I have a TLC Mini LED TV which is great as a TV though.

Could you point me in the direction of some actual chocolate please

This is not an open source application. Here is the definition of open source should you wish to correct your post - https://opensource.org/osd

Disabling offline accounts is one thing but scanning and labeling your files to profile users is a whole other can of worms. This trajectory leads to zero privacy for the user and I feel like switching to Linux/Mac will be the only option sadly.

This website is pure art. I enjoyed visiting.

Excellent resource. The videos link to a YouTube channel with a treasure trove of content in multiple disciplines. Thanks for sharing!

Great write up!

Does batching add data from multiple requests into the same context, potentially decreasing perplexity? If so, are we trading off perplexity for lower operating costs?

As it happens, you are creating a time constraint.

It's hilarious! Well done :)