111–120 of 163 posts
Earlier quoted context omitted.
100x is a bold statement.
You can easily get to 100x in a greenfield project but you will never get to 100x in a legacy codebase.
It made me think that one of the things that it probably needs is a way to get a 'feel' for the game in motion. Perhaps a protocol for encoding visible game state into tokens is needed. With terrain, game entity positions, and any other properties visible to the player. I don't think a straight autoencoder over the whole thing would work but a game element autoencoder might as a list of tokens.
Then the game could provide an image for what the screen looks like plus tokens fed directly out of the engine to give the AI a notion of what is actually occurring. I'm not sure how much training a model would need to be able to use the tokens effectively. It's possible that the current embedding space can hold a representation of game state in a few tokens, then maybe only finetuning would be needed. You'd 'just' need a training set of game logs with measurements of how much fun people found them. There's probably some intriguing information there for whoever makes such a dataset. Identifying player preference clusters would open doors to making variants of existing games for different player types.
Earlier quoted context omitted.
Ah!! I didn’t even realize I could upgrade. Thanks!
Um, you can’t ^^’. The key is to use the rewind power very sparingly, only as long as it’s required to destroy the enemy. This way you’ll guarantee you will be in the net positive energy generation for the first 2-3 waves. You should be able to afford the 2nd tower by the end of Wave 2.
[flagged]
This is awesome. I've been in software for 20+ years now as well. One thing I've noticed is many (most?) people in our cohort are very skeptical of AI coding (or simply aren't paying attention). I recently developed a large-ish app (~34k SLOC) primarily using AI. My impression is the leverage you get out of it is exponentially proportional to the quality of your instructions, the structure of your interactions, and t…
> the leverage you get out of it is exponentially proportional to the quality of your instructions, the structure of your interactions, and the amount of attention you pay to the outputs Couldn't say it better myself. I think many people get discouraged when they don't get good results without realizing that for good results you need to learn how to interact with these AI agents, it's a skill that you can improve by…
"Prompt" or "context engineering" is what grifters claim they can teach for a fee.
What does make a difference is what has been obvious since the advent of LLMs: domain experts get the most out of them. LLMs can be coaxed into generating almost any thinkable output, as long as they're prompted for it. Only experts will know precisely what to ask for, what not to ask for, and whether or not the output aligns with their expectations. Everyone else is winging it, and their results will always be of inferior quality, until and if these tools improve significantly.
What's dubious to me is whether experts really gain much from using LLMs. They're already good at their job. How valuable is it to use a tool that can automate the mechanical parts of what they do, while leaving them with larger tasks like ensuring that the output is actually correct? In the context of programming, it's like pairing up with a junior developer in the driver seat who can type really quickly, but will confidently make mistakes or will blindly agree with anything you say. At a certain point it becomes less frustrating and even faster to type at normal human speeds using boring old tools yourself.
Earlier quoted context omitted.
> the leverage you get out of it is exponentially proportional to the quality of your instructions, the structure of your interactions, and the amount of attention you pay to the outputs Couldn't say it better myself. I think many people get discouraged when they don't get good results without realizing that for good results you need to learn how to interact with these AI agents, it's a skill that you can improve by…
It's not about learning how to interact with AI agents. The only required skills for working with these tools are basic reading and writing skills any decent English speaker would have. Knowing how and when to provide additional context and breaking down problems into incremental steps are common workflows within teams, not something novel or unique to LLMs. "Prompt" or "context engineering" is what grifters claim th…
This is flatly untrue, just as the same would be untrue about getting the most out of people (but the behavioral quirks of AI systems and the ways to deal with them do not follow human psychology, so while it is inaccurate in the same way as with people, the skills needed are almost entirely unrelated.)
Earlier quoted context omitted.
I use it at work everyday. I work with people who use it everyday. 100x is complete and utter nonsense. 100x means that I can finish something that would have taken me 10 years in a little over a month. It would be obvious not because people are posting “I get a 100x productivity boost”, but because show HN would be filled with “look at this database engine I wrote in a month”, and “check out this OS that took me 2 m…
You’re missing the point by bike shedding on “100x” It’s probably higher tbh because there’s things I prototyped to test an assumption on, realized it was O(N^2) then dumped it and tried 4 more architecture simulations to get to one that was implementable with existing tool chains I know So you’re doing exactly what i called out which is evaluating it as a magic oracle instead of what I said which is that it makes me…
Earlier quoted context omitted.
Better spoons, better food.
Spoons are tools you use to consume food; a better analogy would be better kitchen, better food. An induction range, quality good, nice pans, nice knives will definitely enable higher quality food. Of course you can still make crap if you don’t know what you’re doing, the point is that the tools raise the ceiling for someone who does know what they’re doing.