artemium

[Question] What are the chances that Su­per­hu­man Agents are already be­ing tested on the in­ter­net?

• artemiumJan 10, 2025, 11:34 AM

  1 point

  0

  on: Is Musk still net-pos­i­tive for hu­man­ity?

  The answer surely depends mostly on what his impact will be on AI developments, both through his influence on the policy of the new administration and what he does with xAI. While I understand that his political actions might be mind-killing (to say the least) to many of his former fans, I would much prefer a scenario where Elon has infuriating politics but a positive impact on solving alignment over one with the opposite outcome.

• artemiumDec 26, 2024, 2:54 PM

  33 points

  8

  on: artemium’s Shortform

  A new open-source model has been announced by the Chinese lab DeepSeek: DeepSeek-V3. It reportedly outperforms both Sonnet 3.5 and GPT-4o on most tasks and is almost certainly the most capable fully open-source model to date.

  Beyond the implications of open-sourcing a model of this caliber, I was surprised to learn that they trained it using only 2,000 H800 GPUs! This suggests that, with an exceptionally competent team of researchers, it’s possible to overcome computational limitations.

  Here are two potential implications:

  1. Sanctioning China may not be effective if they are already capable of training cutting-edge models without relying on massive computational resources.

  2. We could be in a serious hardware overhang scenario, where we already have sufficient compute to build AGI, and the only limiting factor is engineering talent.
     
     (I am extremely uncertain of this, it was just my reaction after reading about it)
     

artemium’s Shortform

• artemiumOct 17, 2024, 11:08 AM

  7 points

  0

  in reply to: avturchin’s comment on: Bit­ter les­sons about lu­cid dreaming

  Perhaps Randolph Carter was right about losing access to dreamlands after your twenties:
  
  When Randolph Carter was thirty he lost the key of the gate of dreams. Prior to that time he had made up for the prosiness of life by nightly excursions to strange and ancient cities beyond space, and lovely, unbelievable garden lands across ethereal seas; but as middle age hardened upon him he felt these liberties slipping away little by little, until at last he was cut off altogether. No more could his galleys sail up the river Oukranos past the gilded spires of Thran, or his elephant caravans tramp through perfumed jungles in Kled, where forgotten palaces with veined ivory columns sleep lovely and unbroken under the moon.
  
  Btw, have you heard about PropheticAI? They are working on device that is supposed to help you with lucid dreaming?

• artemiumJul 11, 2024, 7:39 AM

  3 points

  0

  in reply to: leogao’s comment on: Daniel Koko­ta­jlo’s Shortform

  Still think it will be hard to defend against determined and competent adversaries committed to sabotaging the collective epistemic. I wonder if prediction markets can be utilised somehow?

• artemiumJun 24, 2024, 7:43 AM

  6 points

  1

  on: How are you prepar­ing for the pos­si­bil­ity of an AI bust?

  I am not sure if dotcom 2000 market crash is the best way to describe a “fizzle”. The upcoming Internet Revolution at the time was a correct hypothesis its just that 1999 startups were slightly ahead of time and tech fundamentals were not ready yet to support it, so market was forced to correct the expectations. Once the tech fundamentals (internet speeds, software stacks, web infrastructure, number of people online, online payments, online ad business models etc...) became ready in mid 2000s the Web 2.0 revolution happened and tech companies became giants we know today.
  
  I expect most of the current AI startups and business models will fail and we will see plenty of market corrections, but this will be orthogonal to ground truth about AI discoveries that will happen only in a few cutting edge labs which will be shielded from temporary market corrections.
  
  But coming back to the object level question: I really don’t have a specific backup plan, I expect even the non-AGI level AI based on the advancement of the current models will significantly impact various industries so will stick to software engineering for forceable future.

• artemiumMar 1, 2024, 9:11 AM

  3 points

  0

  in reply to: Daniel Kokotajlo’s comment on: China-AI forecasts

  My dark horse bet is on 3d country trying desperately to catch up to US/​China just when they will be close to reaching agreement on slowing down progress. Most likely: France.

• artemiumFeb 26, 2024, 8:57 AM

  1 point

  0

  in reply to: Daniel Kokotajlo’s comment on: China-AI forecasts

  Why so? My understanding is that, if AGI will arrives in 2026 it will be based on the current paradigm of training increasingly large LLMs on massive clusters of advanced GPUs. Given that US has banned selling advanced GPUs to China, how do you expect them to catch up that soon?

• artemiumJun 10, 2023, 1:30 PM

  15 points

  5

  in reply to: Razied’s comment on: EY in the New York Times

  To add to this point, author in question is infamous for doxxing Scott Alexander and writing a hit piece on rationalist community before.
  
  https://​​slatestarcodex.com/​​2020/​​09/​​11/​​update-on-my-situation/​​
  
  

• artemiumNov 28, 2022, 12:54 PM

  7 points

  1

  in reply to: Viliam’s comment on: So­cial­ist firms as a cause area

  I was also born in a former socialist country -Yugoslavia, which was notable for the prevalence of worker-managed firms in its economy. This made it somewhat unique among other socialist countries that used a more centralized approach with state ownership over entire industries.
  
  While it is somewhat different than worker-owned cooperatives in modern market economies it does offer a useful data point. The general conclusion is that they work a bit better than a typical state-owned firm, but are still significantly worse in their economic performance compared to the median private company. This is the reason why despite having plenty of experience with worker-managed firms almost all ex-YU countries today have economies dominated by fully private companies and no one is really enthusiastic about repeating the worker-managed experiment.

• artemiumOct 3, 2022, 12:03 PM

  4 points

  0

  in reply to: Viliam’s comment on: A Few Ter­rify­ing Facts About The Russo-Ukrainian War

  Also agree about not promoting political content on LW but would love to read your writings on some other platform if possible.

• artemiumOct 3, 2022, 11:54 AM

  1 point

  0

  in reply to: Roko’s comment on: A Few Ter­rify­ing Facts About The Russo-Ukrainian War

  If it reaches that point, the goal for Russia would not be to win but to ensure another side loses too, and this outcome might be preferable (to them) to a humiliating conventional defeat that might permanently end Russian sovereignty. In the end, the West has far more to lose than Russia and the stakes aren’t that high for us and they know it.

• artemiumOct 3, 2022, 11:49 AM

  5 points

  3

  in reply to: TAG’s comment on: A Few Ter­rify­ing Facts About The Russo-Ukrainian War

  No. I think everything else is in crappy shape cause the Nuclear arsenal was always a priority for the Russian defense industry and most of the money and resources went there. I’ve noticed that the meme “perhaps Russian nukes don’t work” is getting increasingly popular which can have pretty bad consequences if the meme spreads and emboldens escalation.
  
  It is like being incentivized to play Russian roulette because you hear bullets were made in a country that produced some other crappy products.

• artemiumMay 16, 2022, 7:44 PM

  1 point

  on: The AI Count­down Clock

  Looks awesome! Maybe there could be extended UI that tracks the recent research papers (sorta like I did here) or SOTA achievements. But maybe that would ruin the smooth minimalism of the page.

• artemiumMar 14, 2022, 10:05 AM

  4 points

  in reply to: Mitchell_Porter’s comment on: New GPT3 Im­pres­sive Ca­pa­bil­ities—In­struc­tGPT3 [1/​2]

  You can also play around with open-source versions that offer surprisingly comparable capability to OpenAI models.

  Here is the GPT-6-J from EleutherAI that you can use without any hassle: https://​​6b.eleuther.ai/​​

  They also released a new, 20B model but I think you need to log in to use it: https://​​www.goose.ai/​​playground

• artemiumFeb 22, 2022, 9:41 AM

  2 points

  on: Con­voy Crackdown

  I think there could be a steelman why this post is LW-relevant (or at least possible variants of the post). If this Canadian precedent becomes widely adopted in the West everyone should probably do some practical preparation to ensure the security of their finances.

  P.S: I live in Sweden which is an almost completely cashless society, so a similar type of government action would be disastrous.

• artemiumDec 29, 2021, 1:51 PM

  4 points

  in reply to: Srdjan Miletic’s comment on: Why did Europe con­quer the world?

  You can add Black Death to the list. Popular theory is that disease killed so many people (around ¹⁄₃ of Europe’s population) that few remaining workers could negotiate higher salaries which made work-saving innovations more desirable and planted the seeds of industrial development.
  
  

• artemiumDec 3, 2021, 4:52 PM

  11 points

  on: Rus­sian x-risks newslet­ter fall 2021

  This is very underrated newsletter, thank you for writing this. Events in KrioRus are kind of crazy. I cannot imagine a business where it is more essential to convince customers of robustness in the long run than cryonics and yet...ouch.

  Also, Russia deployed lasers Peresvet which blind American satellites used to observe nuclear missiles.

  I thought Peresvet is more of a tactical weapon?
  
  https://​​en.wikipedia.org/​​wiki/​​Peresvet_(laser_weapon)

  Are there any updates on nuclear powered missile, Burevestnik?

• artemiumNov 15, 2021, 9:03 AM

  3 points

  in reply to: maximkazhenkov’s comment on: What would we do if al­ign­ment were fu­tile?

  Even worse, that kind of move would just convince the competitors that AGI is far more feasible, and incentivize them to speed up their efforts while sacrificing safety.

  If blocking Huwaei failed to work a couple of years ago with an unusually pugnacious American presidency, I doubt this kind of move would work in the future where the Chinese technological base would be probably stronger.