149 karma · joined October 22, 2024
I have several agents runing in parallel, they require inputs every 1 to 5 minutes.
Im switching context all the time, and I must hold a larger context in my brain RAM instead of being focused on a single topic.
I'm not writing code anymore for web development.
On the other side, when doing game dev, with all the spatial geometry necessary, LLM are useless 97% of thr time.
They had everything, money, talent, network and hype.
How can it lead to such a disaster?
What I do is to write pure functions with LLM. Once I designed the software and I have the API, I can tell the model to write a function which does a specific job where I know the inputs and outputs but I'm lazy to write the code itself.
I'm not fuding LLM, I use it everyday, all the time. But it won't make me a better engineer. And I deeply believe that becoming a good engineer helped me becoming a better human, because how the job make you face your own limits, train you to be humble and constantly learning.
Vibe coding won't lead to that same and sane mindset.
Lot of cool cpp to write
Second, not all IAP are abusive, I didn't said nor meant that.
https://dictionary.cambridge.org/dictionary/english/monetize
In-game ads are a cancer, breaking the immersion and the game flow.
That's part of why I don't wanna work on mobile gaming anymore, monetization is parasital to the experience or simply abusive thanks to the worst cognitive manipulations. https://www.deceptive.design/types
The other reason I don't want to work on mobile is the dependance (read no choice) to apple and google, see what happens to Fortnite.
On PC, you can distribute yourself and still be extremely successful (kudos to Vintage Story team).
Players prooved countless times that they will buy and even fund experiences they enjoy or are promised to enjoy (which can lead to another set of problems but it's not the topic). So I prefer to rely on gamers buying my game.
- it's great to fill areas with kinda non repetitive patterns which feels random-ish
- it's useless to build anything structured. Eg. You can't guarantee that a path exists from the entrance of the dungeon and the exit/goal.
I ended up doing it fully with traditional Procgen techniques, I'm easily at 100+ hours of work and it's still only half of it.
Discussions about "the problem of proc gen" in games are missing the point. Procgen is a non-gameplay feature, and it's very time consuming to get it right and controlled. The legend that you "gain" time is hilarious when you know how complicated things become with "random generation".
Proc gen is a fantastic tool to bring diversity to non-interesting zones.
The game is in the point of interests, they host goals, challenges, (storyline), progression. All of that is directed by logic.
Also I'm not speaking about making a game engine along with the game.
Having a kernel dev job is different than making your own kernel, speaking on a "world builder" perspective.
Making video game is also like creating your own world!
And it's order of magnitude less hard than making an OS...
Bonus point, you have a chance to make a living from it!
Don't get me wrong, it will output the code faster than me. But overall, i will spend more time prompting + correcting, especially when I want to achieve special designs which are not looking like basic "bootstrap". It's also much less enjoyable to tweak a prompt than just spitting jsx/tw which doesn't require lot of effort for me.
I don't have a demo to justify my claim and I'm totally fine if you dismiss my message because of that.
I recon that I don't like front ending with LLM yet, maybe one day it will.be much better.
My website where I tried some LLM stuff and been disapointed https://ardaria.com
Now I mostly JSX / tailwind, which is way faster than prompting, but surely because I'm fluent in that thing.
On the other side, I'm switching to game dev and it became a very useful companion, outputing well known algorithms. It's more like an universal API rather than a junior assistant.
Instead of me taking time to understand the algo in the details then implementing, I use GPT4o to expand the Unreal API with missing parts. It truly expands the scope I'm able to handle and it feels good to save hours that compounds in days and weeks of work.
Eg. 1. OOB and SAT https://stackoverflow.com/questions/47866571/simple-oriented...
2. Making a grid system using lat/long coordinates for a voxel planet.
Reasoning "the process of thinking about something in order to make a decision"
Thinking: "the activity of using your mind to consider something"
Mind: "the part of a person that makes it possible for him or her to think, feel emotions, and understand things"
I conclude that "An algorithm that searches for the highest probability answer" is not described by "reasoning"
I also think that the definition of Mind of Cambridge is incomplete and lacks the creativity part along with cognition and emotions. But it's a vastly different topic.
EDIT: https://www.width.ai/post/what-is-beam-search
So the wider the beam, the better the outcome?
Yep, no reasoning, just a marketing term to say "more accurate probabilities"
--- The reasoning lies in the concept of mass and weight. The weight of an object is determined by its mass, not its material.
1. Mass comparison:
2kg of feathers has a mass of 2 kilograms.
1kg of lead has a mass of 1 kilogram.
Since 2 kilograms is greater than 1 kilogram, the feathers are heavier.
2. Irrelevance of material:
The type of material (feathers or lead) does not change the mass measurement.
Lead is denser than feathers, so 1kg of lead takes up much less space than 2kg of feathers, but the weight is still based on the total mass.
Thus, 2kg of any substance, even something as light as feathers, is heavier than 1kg of a dense material like lead.
Isn't it a LLM with an algo wrapper?
TBH I freaked out when Unshrouded trailer got released because it's a direct competitor and how cool their game is !