flockonus

> have LMMs hallucinate an entire operating system (...) technically it's now proven to be technically possible

You're comparing apples to oranges there!

To hallucinate is arbitrary, you can use a 2B image param model, it will hallucinate an OS no problem* running real time!

What this post is about is completely different, which is actually emulating the complete system in an LLM - that is hundreds (or more) times slower.

*absulutely crappy quality tho, unusable OS in practice

Some food for thought, if someone from oAI can't make a direct recommendation for something as direct as "Technical documentation is such a multidimensional skill" - how could we know assess what model to use?

Yeah from an objective truth seeking perspective, and i agree with you, it's hard and often times impractical.

About 2y ago, before AI was all the rage - lookup: controversy, scientific fraud networks, "paper mills"

Yes from a social proof perspective.. not really from an objective truth seeking perspective, the best liar tell truths 99% of the time.

This clearly hit a nerve in very interesting ways!

Suppose we have a very convincing math PhD impersonator, agreeing and making some prepared smart-sounding comments saying they understood the proof and it seems to make sense - would it?

Well, most would say - NO! Obviously not, knowing this person was an impersonator. Others now knowing could be convinced of the validity.

Very simple thought exercise that allows to conclude, someone "saying they understood" (or agree) bears absolutely no weight to something's validity.

Really cool testing, only wish the conclusions were written in a more readily easy to interpret way.

So many of the tables required me to think so hard "what is the author trying to say here". Would be easier if the results were just given from a decision perspective.

One example: "Its own server or twenty people?" and the axis is "share of versions" ... makes no sense until read the fine print and interpret it.

Opus 5.5 has the personality of a proud righteous nerd, definitely incomprehensible at times, unless you explicitly tells it to slow it down, it crams information far too dense.

Great model to architect and resolve eng. problems in a harness loop tho. Poor handoff.

<picture> is indeed the right thing from the FE solution standpoint.

Still, unjustified in the pipeline and feature as a whole. Makes no sense to add another format to the pipeline, even if that format saves ~30% on size. Now i need to store 170% of the image size from before & have extra complexity to deal with.

It is a bit hilarious that most of the "apps" open faster in a fake desktop simulated inside the browser than it actually does natively on my Macbook Pro

*yes i know, not apples to apples.

Agreed, record and transcribe however you can and then use a LLM to clear out.

I prompt it to:

"Attached (or underneath) is the transcript of a self recording i've done with tons of rambling and some incorrect words transcriptions, please do a pass clearing out and arranging any typos or possible misunderstandings. Keep original in parenthesis when not sure if it's a misunderstanding. Do not summarize or alter the nature of the content, simply tidy the transcript."

> Are you saying that the percent it'll be in six months isn't relevant to you, or something?

It absolutely is relevant.. but only in about 6 months :)

Suppose the obvious case, i have some resizing pipeline for images. Would i include support today in my resizing pipeline today and pay a few extra cycles and storage for someone that my clients can't read?

It would be cool to have a subscribed alert for when the tech crosses a certain % threshold adoption so i can look at it again, otherwise it just relies on my brain's flawed long term cron job

Not really.. caniuse is quite literal to its name, as a web dev that's what orients what tech i pick up to deploy today.

Anything below ~90ish% is no go, unless i have a fallback strategy of some sort.

> it’s really impressive how much intelligence per dollar has grown in just a few short months.

Open weights models giving a distant salute from afar