I have no interest in anything crypto, but they are making a proposal about NFTs tied to AI (LLMs and verifiable machine learning) so they can make ownership decisions.

So it'd be alive in the making decisions sense, not in a "the technology is thriving" sense.

Wait, what does NFTs have to do with RAG?

I, for one, find NFT-shilling to be a strong signal that I should downgrade my trust in everything else a person says.

Nothing, I think they're just pointing out a seeming lack of awareness of what really is or isn't dead.

Yes, and IMO Superpowers is better when you want to Get Not-Shit Done.

Get Shit Done is best when when you're an influencer and need to create a Potemkin SaaS overnight for tomorrow's TikTok posts.

> TL;DR They solved something to make post less expensive because they cut corners during production.

FWIW having watched the entire thing, they never blamed bad production staff or unavoidable constraints. Those are things that anyone working with others experiences when making anything, whether it's YouTube videos or enterprise software products. My TLDR is: "Chroma keying is an fragile and imperfect art at best, and can become a clusterf#@k for any number of reasons. CorridorKey can automatically create world-class chroma keys even for some of the most traditionally-challenging scenarios."

When you watch the video it becomes pretty clear why it wouldn't be able to do that, although it's fun to think about how a future iteration or alternative might be able to credibly (if you don't look too hard) mimic that someday.

> Additionally, JPEG XS compressed content is indistinguishable from the original uncompressed content.

It can be indistinguishable, as long as you stick with lossless or very low compression ratios. It falls apart at typical JPEG XL compression ratios.

Source: https://github.com/steeltroops-ai/blackhole-simulation

If I may "yes, and" this: spec → plan → critique → improve plan → implement plan → code review

It may sound absurd to review an implementation with the same model you used to write it, but it works extremely well. You can optionally crank the "effort" knob (if your model has one) to "max" for the code review.

A blanket follow-up "are you sure this is the best way to do it?"

Frequently returns, "Oh, you are absolutely correct, let me redo this part better."

You should start a new session for the code review to make sure the context window is not polluted with the work on implementation itself.

At the end of the day it’s an autocomplete. So if you ask “are you sure?” then “oh, actually” is a statistically likely completion.

> You should start a new session for the code review to make sure the context window is not polluted with the work on implementation itself.

I'm just a sample size of one, but FWIW I didn't find that this noticably improved my results.

Not having to completely recreate all the LLM context neccessary to understand the literal context and the spectrum of possible solutions (which the LLM still "knows" before you clear the session) saves lots of time and tokens.

Interesting, I definitely see better results on a clean session. On a “dirty” session it’s more likely to go with “this is what we implemented, it’s good, we could improve it this way”, whereas on a clean session it’s a lot more likely to find actual issues or things that were overlooked in the implementation session.

Many people conflate "AI" and "AGI". It's disappointing to find people who don't know the difference on HN, though.

My fellow Californians would agree that, yes, ET is an alien time. https://en.wikipedia.org/wiki/Eastern_Time_Zone

Brazil have 3 tz, but officially we have just one. We are a vertically country :)

You and China both https://www.timeanddate.com/time/zone/china

Closing a single lab is not fascism. It becomes fascism when a regime systematically targets institutions that produce independent knowledge that doesn't align with Dear Leader's propoganda.