TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Edgar, build a Dyson swarm

222 pointsby whb101about 1 year ago

28 comments

smsm42about 1 year ago
(Spoilers)<p>It takes Edgar 54 days to build a swarm taking metallic elements from all sources, including living organisms. But then when instructed not to harm living organisms, it still takes Edgar 54 days to do the same. Extracting metals from humans can&#x27;t be the most efficient - or even in the top 100 of most efficient, likely - way to get metals. So why would Edgar do that?<p>Also, how Edgar is supposed to be responsible for ensuring humans do not go to war for energy sources and that new technology can not be used ever to harm humans? Pretty much any high-energy technology (and by high-energy I mean something from the muscle power of a human upwards) can be used for harm. These conditions are clearly impossible.
评论 #39858152 未加载
评论 #39859270 未加载
评论 #39866471 未加载
评论 #39858091 未加载
ivanjermakovabout 1 year ago
I would not call this a game. I liked the story but this would&#x27;ve been more convenient as a blog post.
评论 #39858224 未加载
ajucabout 1 year ago
(Spoilers)<p>The fact that Edgar reports on the consequences that we find disturbing about the unsuccessful attempts and the fact that he can predict human behaviour in some of the scenarios (like the fact that the project will be reassigned) - indicate that Edgar knows what we mean in the first place, and does something else in these hypothetical scenarios on purpose.<p>If Edgar really didn&#x27;t knew that taking iron from human blood is a problem - he wouldn&#x27;t be reporting on it (like he ignored billion other factors in each scenario).<p>This indicates bad will and possibly a manipulation attempt, which means the project is a no-go no matter the response in the scenario.
评论 #39858795 未加载
评论 #39858342 未加载
评论 #39859757 未加载
recursiveabout 1 year ago
How is it that displaying text can be churning through so many CPU cycles? My whole laptop is slowed to a crawl.
评论 #39856609 未加载
评论 #39858605 未加载
评论 #39856553 未加载
评论 #39864189 未加载
1nd1ansumm3rabout 1 year ago
I tried to get through the intro but it never seems to end. Is there a game to be played at some point? Thanks.
评论 #39856312 未加载
评论 #39856333 未加载
troutwineabout 1 year ago
Is this meant to be a game? I am unable to type my own prompt, the site is filling its own prompt in and then requesting that I press enter to allow it to do so again. I figured there was an intro but the self-play is more and more elaborate without handing it over to the player.
评论 #39855928 未加载
评论 #39855915 未加载
评论 #39855952 未加载
ChilledTonicabout 1 year ago
Isn&#x27;t it kind of sad that we seem to have stopped writing science fiction that has any hope of a successful future?<p>The moral of the story with Edgar seems to be to never leverage technology to do anything at all.
评论 #39857381 未加载
评论 #39856864 未加载
评论 #39857144 未加载
1nd1ansumm3rabout 1 year ago
I am thinking back to an IOS game called FlappyBird. The creator intentionally aimed for game dynamics that would hook users in the first 30 seconds. As a result, the gameplay mechanics were quite shallow and limited. But on the flip side, the game gained a huge following. You might do some balancing here, not to say there must be instant gratification but a better lead into the gameplay might help.
评论 #39857334 未加载
评论 #39857166 未加载
评论 #39857094 未加载
gillhabout 1 year ago
Have to provide precise instructions to LLMs to get anything useful.<p>Instructions for operating the &quot;Holy hand grenade of Antioch&quot; from Monty Python and the Holy Grail are a good example:<p>&#x27;&#x27;First shalt thou take out the Holy Pin. Then shalt thou count to three, no more, no less. Three shall be the number thou shalt count, and the number of the counting shall be three. Four shalt thou not count, neither count thou two, excepting that thou then proceed to three. Five is right out. Once the number three, being the third number, be reached, then lobbest thou thy Holy Hand Grenade of Antioch towards thy foe, who, being naughty in My sight, shall snuff it.&#x27;
yoavabout 1 year ago
I don’t understand the game.<p>I tapped the screen maybe 30 times and went through it typing to itself and failing and succeeding at different tasks.<p>If I kept going would I eventually get to type something?
评论 #39856947 未加载
0cf8612b2e1eabout 1 year ago
In case anyone has not tried it, the Dyson Sphere Project on Steam is tremendous fun. A different spin on the Factorio gameplay loop.<p>I completed it before combat was added, and enjoyed the low stress environment.
评论 #39856967 未加载
评论 #39856574 未加载
评论 #39857563 未加载
评论 #39857298 未加载
评论 #39861112 未加载
评论 #39856915 未加载
snapcasterabout 1 year ago
Just let me play quicker. I got the point after the first example and then seemed like I had to watch endless examples (gave up before getting to the point where I could type the prompts)
评论 #39857020 未加载
eddierogerabout 1 year ago
It&#x27;s like Universal Paperclips with a plot. Neat.
评论 #39856953 未加载
评论 #39859822 未加载
评论 #39857125 未加载
评论 #39857185 未加载
dostickabout 1 year ago
The punchline is that crab was wrongfully accounted for in all simulation? Or that this is millionth cycle of earth civilisation and through all cycles crab self-trained and developed into most sophisticated organism and done to us same as we would do to them?
squigzabout 1 year ago
That was funny. Gotta watch out for those crabs...
评论 #39856595 未加载
yu3zhou4about 1 year ago
A short but nice experience, with pleasant UI and a bit of fun of prompting. Thanks for sharing and good job :) Maybe try longer forms as well because maybe you might find yourself in writing scifi
评论 #39856913 未加载
wigivabout 1 year ago
Reminds me of the &quot;Exact Instructions Challenge&quot; videos where kids write instructions for some everyday task - like making a PB&amp;J sandwich - and parents, hilariously, follow the instructions verbatim.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=cDA3_5982h8&amp;list=PL2tgThFV6OzlR3yFLtH1m8LAzzl-JVrFR" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=cDA3_5982h8&amp;list=PL2tgThFV6O...</a>
darepublicabout 1 year ago
This seems to be a showcase of web dev skills. The story and atmosphere is OK, but the single tree node with null at the end of both branches is a let down. Also after choosing one ending, it was annoying to go through all the old dialogue to get back. On the whole though I liked it
dgrin91about 1 year ago
Fun, but you need a way to skip the intro after the first playthrough. Its way too long to sit through everytime.
konstantinua00about 1 year ago
&quot;play&quot; in the address is misleading, yeah<p>otherwise it&#x27;s a very nice story<p>great in its simplicity, fails in its simplicity
dreamcompilerabout 1 year ago
I think the lesson here is that you can&#x27;t fix AI alignment issues by throwing adjectives and adverbs at the problem.
wccrawfordabout 1 year ago
Holy crap. Reading that slowly is <i>painful</i>. Can you please give an option to make it instant, or at least speed it up 2x-3x?
评论 #39856794 未加载
jes5199about 1 year ago
yes, this is what we thought robots would be like before we had LLMs
评论 #39856544 未加载
geniiumabout 1 year ago
I must be too tired for this kind of stuff.
sugarkjubeabout 1 year ago
Edgar must feel the same as many software engineers.<p>Clients ask you to implement something. When you deliver what they wanted, they change their mind and come with new requirements they didn&#x27;t bother to mention before. Every. Single. Time.
评论 #39862299 未加载
srackeyabout 1 year ago
I wrote this comment:<p>“ Prediction: Eliezer Yudkowsky will go down as the most mind-destroying author since Karl Marx. Another: you ask the AI genie god to do something and it annihilates humanity. Ahhhh! Air strike all the data centers! “ and it got flagged within 15 minutes.<p>Seems that the AI cultists and or Marxists already are too embedded here. Perhaps it was a bit inflammatory, but I know many folks who have been utterly pwned by AI safety brainworms, and the “game” linked is the same argument we’ve seen a million times. It would be a shame if AI was the next nuclear power: a promising tech kneecapped by what are essentially religious activists.<p>Religious activism posing as secularism seems to be a weak spot in our collective thinking.
评论 #39856231 未加载
iwontberudeabout 1 year ago
I made it like 4 seconds before I hit back
userbinatorabout 1 year ago
I was somewhat disappointed since I clicked expecting something about a swarm of vacuum cleaners.