Hacker Newsnew | past | comments | ask | show | jobs | submit | albelfio's commentslogin


The doom demo is also in the article, for anyone that doesn't want to go to X.com. :)


The doom video is also in the article itself (headline: "Doom").

I suppose this is the same video as the one from the parent comment, but I don't know for sure - I don't have a twitter account and the above link doesn't work for me.


I linked to the tweet that has the video because if you are not signed in you cannot see the whole thread of tweets.

I can see the individual tweets in the browser while not signed in though.


I'm not sure the authors realize this is way more than "just a cool demo": if this holds up, it's going to be huge for game QA work.

Instrument your game to output properties of entities near the player and the output is the various control inputs - moment to moment gameplay gets solved. Maybe augment with a tick-by-tick controlled stepping mode if particularly twitchy - an LLM can take care of the higher level reasoning then.


yes; and it could also be used to spot unexpected behavior such as inputs not registering due to rare bugs

Link to a raw MP4 of the video, from the parent article: https://framerusercontent.com/assets/rlL7ImEbISFoYt3IJEHHfvj...

It's in the parent article under a section named "Doom" in case that asset URL ever changes.


But when their system is given the instruction "do not fire, simply dodge" - it doesn't "simply dodge", it actually gets close to the fleshy pink demon rather than keeping its distance. Or am I misunderstanding?

i think its just telling the model that it cant output a shoot action

Doesn't this mean Jev can be used to drive a car as well?

lol! they reinvented aim bot for cheaters.

Yes, we called API - Actual Person Interface. One person on one side of the marketplace that does the heavy work to build the other side, kickstart the flywheel


Is there a way to evaluate the impact of these errors in the day2day use of Claude Code? Is it a security risk?


What the governments have done is different from what the cultural values of the two countries are. Chinese values and American values are different, and people can argue for one or the other. We, westerner, want our values to prevail. Dwarkesh wants to preserve our values of freedom.


> We, westerner, want our values to prevail.

This comes to the core of the issue, and is where I think the disagreement comes from. Many Westerners in fact do not want "Western" values to prevail.

Why? For me those values have led to outcomes so horrendously antithetical to _my_ values, that I would not wish them for the rest of the world. Even worse, this Western centrism has led to jingoist conclusions for at least 400 years.


Missions should evolve with the stage of the company. Their last mission is direct and neat. The elimination of the sentence "unconstrained by a need to generate financial return" does not have any negative connotation per se.




How fast will Google come with their version? How slow will be Safari to adopt it?


I wrote a simplistic blog about the subject. While limited, it treats a topic I have not seen around yet


Sst.dev and remix.run are a pleasure to work with


Another vote for SST!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: