Theme: AI

  • the only GPT text is the third paragraph from the end. So my text is jarring? lo

    the only GPT text is the third paragraph from the end. So my text is jarring? lol


    Source date (UTC): 2024-03-29 22:51:45 UTC

    Original post: https://twitter.com/i/web/status/1773845529270640930

    Reply addressees: @LiminalRev @DwightExMachina @radiofreenw

    Replying to: https://twitter.com/i/web/status/1773816928517447798

  • Prompt: Claude3, please position and summarize the work of youtube historian rud

    Prompt:
    Claude3, please position and summarize the work of youtube historian rudyard lynch and his work under the alias @whatifalthist.

    Response:
    Rudyard Lynch, better known by his YouTube alias “Whatifalthist,” is a popular online historian and content creator who specializes in counterfactual history, geopolitical analysis, and forecasting future events based on historical patterns and trends.

    Position: Whatifalthist’s work is primarily focused on exploring alternative historical scenarios, analyzing the geopolitical landscape, and making predictions about the future of nations and civilizations. His content is often characterized by a mix of historical analysis, political commentary, and speculation, which has earned him a significant following on social media platforms, particularly YouTube.

    Summary of work:

    Counterfactual history: Whatifalthist is known for his “What if?” scenarios, where he explores how historical events might have unfolded differently if certain key factors had changed. These alternative timelines are used to highlight the importance of specific decisions, individuals, or circumstances in shaping the course of history.

    Geopolitical analysis: A significant portion of Whatifalthist’s content focuses on analyzing the geopolitical landscape, both in terms of historical context and current events. He examines the relationships between nations, the role of geography in shaping political dynamics, and the impact of economic, social, and technological factors on global power structures.

    Forecasting future events: Drawing on his understanding of historical patterns and current geopolitical trends, Whatifalthist makes predictions about the future of nations, regions, and the world as a whole. These forecasts often explore potential scenarios, such as the rise or fall of great powers, the emergence of new global challenges, and the long-term consequences of present-day decisions.

    Civilization analysis: Whatifalthist also delves into the factors that contribute to the rise, decline, and collapse of civilizations throughout history. He examines the role of factors such as geography, resources, technology, culture, and institutions in shaping the trajectory of human societies and draws lessons from the past to inform his analysis of the present and future.

    Engaging presentation style: One of the key factors contributing to Whatifalthist’s popularity is his engaging and accessible presentation style. He uses a mix of historical narrative, visual aids, and humor to make complex topics more relatable and easier to understand for his audience.

    While Whatifalthist’s work has garnered a significant following, it is important to note that his content represents a specific perspective and approach to historical analysis and forecasting. As with any public intellectual or content creator, it is essential to critically evaluate his ideas and consider them alongside other sources and viewpoints within the broader context of historical scholarship and geopolitical discourse.


    CD: not bad really. 😉


    Source date (UTC): 2024-03-27 19:39:43 UTC

    Original post: https://twitter.com/i/web/status/1773072427779559424

  • RT @curtdoolittle: THE AI HARD PROBLEMS AREN’T HARD PROBLEMS 1) Consciousness is

    RT @curtdoolittle: THE AI HARD PROBLEMS AREN’T HARD PROBLEMS
    1) Consciousness is possible and it’s not even hard. It’s a natural consequenc…


    Source date (UTC): 2024-03-27 15:07:23 UTC

    Original post: https://twitter.com/i/web/status/1773003891103199653

  • RT @Plinz: I am more afraid of lobotomized zombie AI guided by people who have b

    RT @Plinz: I am more afraid of lobotomized zombie AI guided by people who have been zombified by economic and political incentives than of…


    Source date (UTC): 2024-03-24 08:50:18 UTC

    Original post: https://twitter.com/i/web/status/1771821833110663284

  • Finally. A Strategic move by the USG: —“In an effort to get closer to its ambi

    Finally. A Strategic move by the USG:
    —“In an effort to get closer to its ambitions (and to level the playing field), the US government is hoping a $20 billion cash infusion can take tech giant Intel to new heights (Read: Finally catching up to competitors like Nvidia). The award will allow the California-based company to build and remodel chip plants in four states, with at least one fab site — essentially a semiconductor factory — for AI chips”—


    Source date (UTC): 2024-03-21 13:19:11 UTC

    Original post: https://twitter.com/i/web/status/1770802334026633216

  • No. It’s quite simple if you aren’t ignorant of the subject matter. For the igno

    No. It’s quite simple if you aren’t ignorant of the subject matter. For the ignorant, a ‘feature’ means a ‘variable’ in the context. As such ‘you need more data than variables’ is simply obvious. Which is why he stated the same thing regarding genetics for the same reason.


    Source date (UTC): 2024-03-19 12:34:11 UTC

    Original post: https://twitter.com/i/web/status/1770066236111479139

    Reply addressees: @BobJone77944187 @Glace15840573 @MindEnjoyer

    Replying to: https://twitter.com/i/web/status/1770064525380759901

  • THE IMPORTANCE OF AI HALLUCINATION In case my reason for sharing this post wasn’

    THE IMPORTANCE OF AI HALLUCINATION
    In case my reason for sharing this post wasn’t clear:
    1) “Hallucination is equivalent to ideation” so we WANT the capacity for ideation (hallucination).
    2) The problem is knowing the difference between ideation by hallucination and recitation of… https://twitter.com/pmarca/status/1769440969252892815


    Source date (UTC): 2024-03-17 19:36:16 UTC

    Original post: https://twitter.com/i/web/status/1769447679468113940

  • Hmm… Consider this: 1) there is no limit to language and description 2) there

    Hmm… Consider this: 1) there is no limit to language and description 2) there is no limit to human mental capacity for generalization. 3) the principle value of AI is to allow humans to increasingly focus their energies on generalizations, scale, and the opportunities…


    Source date (UTC): 2024-03-17 19:28:03 UTC

    Original post: https://twitter.com/i/web/status/1769445612586496375

    Reply addressees: @BasedErwin @RunicSigil

    Replying to: https://twitter.com/i/web/status/1769444641290539445

  • I mentioned those technologies because they are all currently in some state of d

    I mentioned those technologies because they are all currently in some state of development, with, I think, next month being the first large scale neuromorphic computer coming online, I think in Australia? (pretty sure). Photonic chips, and three dimensional chips are all in progress. IMO we will see the boom in existing vector compute chips last for a bit and then a crash as those chips are replaced by the neuromorphic. But as in all things I have a very good record of WHAT will happen but timing such things is a fool’s game. 😉

    Reply addressees: @RunicSigil


    Source date (UTC): 2024-03-17 17:32:55 UTC

    Original post: https://twitter.com/i/web/status/1769416640595152896

    Replying to: https://twitter.com/i/web/status/1769415591587442890

  • “Q: What about mentats instead of chips?”– Not possible. The rate of input of i

    —“Q: What about mentats instead of chips?”–
    Not possible.
    The rate of input of information available to human brains, and the rate of integration into memory, and the breadth of paradigms in which information is structured, the precision of that information, synthesis of that information, and the volume of information in and across those paradigms exceeds by orders of magnitude the capacity of the human brain.
    If you learn my (our) work on the unification of the fields and universal commensurability you can significantly improve the disambiguation, organization, synthesis and falsification of the available information. You’ll gain at least a standard deviation in demonstrated intelligence with the same IQ.
    But assuming we either solve the algorithmic problem of the current models and their underlying hardware architecture, or we manage to build large numbers of neuromorphic computers, in three dimensional chips instead of two, and then using photons (light) solving the heat problem, then the necessity of pre-calculation, vast compute, and delayed integration of information, will be circumvented, and at that point leaving human capacity in the dust even more so than now.

    Reply addressees: @RunicSigil


    Source date (UTC): 2024-03-17 17:09:07 UTC

    Original post: https://twitter.com/i/web/status/1769410650399264768

    Replying to: https://twitter.com/i/web/status/1769395685739405761