Artificial intelligence still has some way to go

https://archive.li/HE4Aw

seems to have the most deets so far

might just be first-name based solidarity but i’ve always had a softspot for sam

not clear if the ai security stuff is reference to the eliezer yudkowsky style world destroying ai supervillain or more mundane like gpt5 is way better at enabling fraud etc. but if it’s the former i’m pretty excited for gpt5

this link https://archive.li/HE4Aw doesn't seem to be active for me

unusually acrimonious way to fire a big name ceo over what seems like a strategic disagreement, but i guess we havent heard how he was misleading the board

maybe has something to do with not wanting to deal with saudi

Alongside rifts over strategy, board members also contended with Altman’s entrepreneurial ambitions. Altman has been looking to raise tens of billions of dollars from Middle Eastern sovereign wealth funds to create an AI chip startup to compete with processors made by Nvidia Corp.
...
Sutskever and his allies on the OpenAI board chafed at Altman’s efforts to raise funds off of OpenAI’s name, and they harbored concerns that the new businesses might not share the same governance model as OpenAI, the person said.

btw startup app guy thinking hes going to make a chip company doesnt sound too promising

read some thing about him leaving ycombinator and it was the polar opposite of this they fired him but did it in such a way that the media didnt even realized itd happened, saying that he was switching from ceo to chairman and then that he was advising when really none of that happened he just stopped working there, thats two pretty big firings and he wasnt ceo at either place super long

link?

akm it's this article

https://www.bloomberg.com/news/articles/2023-11-18/openai-altman-ouster-followed-debates-between-altman-board

A month ago, Sutskever’s responsibilities at the company were reduced, reflecting friction between him and Altman and Brockman. Sutskever later appealed to the board, winning over some members, including Helen Toner, the director of strategy at Georgetown’s Center for Security and Emerging Technology.

Seeing some new rumors popping up now. Apparently Microsoft was blindsided and is very displeased with the firing, and now OpenAI might be trying to get Altman back.

This is a guy who started a foursquare clone that had such a successful exit its investors received the same rate of return that you could have beaten with an index tracker. As far as I can tell this is the only accomplishment attributable solely to him. If a goober like this successfully starts a competitor to OpenAI and Anthropic then no one has a moat.

https://www.theverge.com/2023/11/18/23967199/breaking-openai-board-in-discussions-with-sam-altman-to-return-as-ceo

xp to caek

http://www.paulgraham.com/5founders.html

5. Sam Altman

I was told I shouldn't mention founders of YC-funded companies in this list. But Sam Altman can't be stopped by such flimsy rules. If he wants to be on this list, he's going to be.

Honestly, Sam is, along with Steve Jobs, the founder I refer to most when I'm advising startups. On questions of design, I ask "What would Steve do?" but on questions of strategy or ambition I ask "What would Sama do?"

What I learned from meeting Sama is that the doctrine of the elect applies to startups. It applies way less than most people think: startup investing does not consist of trying to pick winners the way you might in a horse race. But there are a few people with such force of will that they're going to get whatever they want.

link?

― 龜, Saturday, November 18, 2023 5:14 PM (one hour ago) bookmarkflaglink

i saw it on twitter when i was searching for rumors last night lol

https://www.theverge.com/2023/11/18/23967199/breaking-openai-board-in-discussions-with-sam-altman-to-return-as-ceo

― 龜, Saturday, November 18, 2023 6:46 PM (five minutes ago) bookmarkflaglink

smh pitiful these people need to touch grass!!

you did one cool thing and now the spreadsheet company is mad at you deal with it

so people were being very conspiratorial about this but it sounds like it was exactly what was suspected: some wing of the board felt like he wasn't as dedicated to safety, governance and guardrails as they believed he should have been, and they acted very quickly and perhaps rashly. This might be some "EA coup" but in this case it's very possible they were correct in their thinking? Anyway sounds like he's probably going to come back so whatever.

Before/after. See what I mean? There's just no comparison. Which would you rather hang in your entryway? How did the AI 'know' exactly what the starting pic needed to complete it? Amazing. pic.twitter.com/SGQOsagQJK

— sonch (@soncharm) November 16, 2023

do people really call him “sama”? like they say sama out loud?

ai sama bin laden

gen z loves both samas

ai sama bin laden

― flopson, Sunday, November 19, 2023 5:28 PM (fifty-eight minutes ago) bookmarkflaglink

lol

Today I resigned from my position as CEO of Cruise. (1/5)

— Kyle Vogt (@kvogt) November 20, 2023

was this forced? they were banned from the road in SF after this accident and maybe lying to the DOJ.

Sorry DMV

cruise has made a series of quite serious mis-steps recently (if you don’t assume the entire project of autonomous driving isn’t a mis-step) so yeah i’d say it was forced and i’m imagine there was a tidy sum behind it.

and altman now with microsoft. the amount of money they must have thrown at him to do that. still, it’s money they’ve got and it made sense to do it and do it quickly. the risk of a new start up would have been huge.

I found this quite moving - and it has an idiotic quote from sam altman!

https://www.newyorker.com/humor/sketchbook/is-my-toddler-a-stochastic-parrot

ai sama bin laden

― flopson, Sunday, November 19, 2023 5:28 PM (yesterday)

*slow clap*

the nighthawks thing is a masterpiece of tone. love his update

https://x.com/soncharm/status/1726305454580756866?s=20

UPDATE: Ok got a chance to skim some replies here, many seem to thing I ‘missed the point’ of the original. But I really don’t agree remember, the AI parses & detects what’s in it (into ‘tokens’) not me. All this info is then being used as a ‘seed’ for the algo. Make sense now?

— sonch (@soncharm) November 19, 2023

It's a good joke but it's crystallised one of the things I won't miss about Twitter - you can just do the joke, you don't have to reply to all of the replies in character and draaaaaaag the joke to death.

Or: jokes good, 'bits' bad

and altman now with microsoft. the amount of money they must have thrown at him to do that. still, it’s money they’ve got and it made sense to do it and do it quickly. the risk of a new start up would have been huge.

― Fizzles, Monday, November 20, 2023 4:40 AM (five hours ago) bookmarkflaglink

when you have an opportunity to light a tiny part of your huge pile of money on fire you gotta take

now 500 of openais employees have signed a letter threatening to go with sam to microsoft unless hes instated, this is funny now but itll be even funnier after the inevitable ai crash

https://pbs.twimg.com/media/F_YbOFxWcAAkIlj?format=jpg&name=medium

the ruling class just doesnt hit like it used to

there is one way microsoft can salvage its investment, one perfect use case, something so revolutionary...

https://i.imgur.com/Qq4puCe.png

clippai

"the nighthawks thing is a masterpiece of tone. love his update"

Really funny as I have a reproduction of Nighthawks. Can't look at it in the same way now.

nighthawks no thanks, dayhawks

ah, that provides the context for this, which made me laugh the other day:

https://x.com/kendrictonn/status/1725296651944751237?s=20

lol i love the anteater nighthawks had totally forgot about that

hahaha that one is great

(its not ai if thats unclear its been floating around the net for a while)

speculation on why microsoft likes ai, makes sense imo, i have my doubts that ai will ever be more than a niche or middling contributor, and its so resource intensive that getting people (or more realistically companies) to pay enough for it to make it profitable is dicey, but microsoft can certainly afford to bet on it

Generative AI might be transformative or it might be another flash in the pan. Either way, the partnership with OpenAI still gave it an advantage over AWS and Google to drive customers to its Azure cloud platform because all those AI tools require a lot of computing power — and that’s really what Microsoft wants to sell people.

https://www.disconnect.blog/p/how-sam-altman-plays-into-microsofts

full disclosure i do pay for the ai product github copilot, its helps you write c0de, you can ask it to write you a whole thing as weve seen in demonstrations of chatgpt but i dont think most people use it that way, where it really shines is code competition ie you start typing and it finishes the line for you, its pretty good! totally not trustworthy tho, you have to check its work

that kind of more focused use of the technology or series of technologies that is for some reason called artificial intelligence seems more realistic than the super wide consumer focused let chatgpt write a term paper for you approach

at $10 a month i have no idea if copilot is profitable for github and their parent... microsoft

it is hard to decouple the marketing hype from the industries actual plans, obvs its good for them if theres a million articles being all ai will change the world even if they dont actually believe it

i'm pretty bullish on generative AI.

like a lot of machine learning technologies, the binary will it/won't it discussions in much of the media often seem detached from the fact that it's already being used successfully in all sorts of industries. speeding up and facilitating the creative ideation process to get more quickly to the point where your concept has enough substance for people to give it a thumbs up or a thumbs down is one example. even in my own area we are using it for quality control purposes, enabling us to more quickly spot serious issues quicker. it's also opened up the ability for non-coding people to describe and generate applications based on concepts, which means more people are able to participate in formerly quite technical areas, reducing the bottleneck to innovation.

a wider lens shows that self-driving vehicles are very successfully used in constrained industrial environments.

the constraints of clean data, algorithm optimisation and GPU are real though, with investment into any of those becoming more demanding for uncertain incremental revenue return - as lag∞n has said, the long-term business model seems extremely uncertain.

everything ive seen ai really generate on its own is so awful to the point of uselessness, at least from my pov but im not some marketing manager maybe they like that shit idk

and yeah profitability is where the rubber meets the road, lots of things that are nice to have eg uber when theyre being subsidized by massive investments are not as nice when you have to pay full price for them

yes, it's unsurprising in retrospect, but coding does seem like an unambiguously useful application for gen AI. And there's a lesson there, imo, in the stark difference between programming languages and regular human ones.

"a wider lens" = yeah this is where the sudden, recent conflation of "AI" with "generative AI, likely text or image generating" is unhelpful. People saying "AI is doomed" are likely not talking about, say, the use of digital twins to do safety checks in the Korean shipbuilding industry or supply chain optimization or etc. I am not at all bullish on autonomous vehicles in the real world, but Fizzles' example sounds like a continuation of the roboticization of industrial environments that began decades ago. I mean, is a Roomba an AI?

even for coding it kind of doesnt make sense for a number of reasons for anything bigger than a snippet IMHO