I was reading the article, but I don't think it's possible to slow the fuck down, honestly. There are too many people who need to discover for themselves what the limits of these AI models are when they push them far.
Maybe some people have already reached that point after so much AI coding and are now warning us; they pushed so hard that they understand the limits. But this is the kind of thing you need to experience on your own.
You need to experiment, learn, test the limits, think for yourself, take as many steps back as you need.
> There are too many people who need to discover for themselves what the limits of these AI models are when they push them far
Why? Next week a new version of Claude and GPT will come out and the limits will change again. Are you really fully testing every new version of every LLM agant to see where its limits are?
Those of us old enough to have seen this cycle before know its a fools game trying to keep up with development pace in the initial bubble. Its much better to wait for development and progress to start plateuing and then its easier to see the wood for the trees.
ai in the sense of a new and immature techology which is constantly evolving and changing?
How about anything on the web? HTML boon in the 90s. Wordpress and PHP frameworks in the 00's, Javascript frontend shadow doms which require hydration in the 10's, node.js and javascript on the server etc etc.
All techonologies which were not worth jumping in during the initial boom becasue it changed so rapidly and it meant relearning concepts with every new release.
Its the same with ai, some prompt which gave amazing results last year might not now, and you need to be aware of what has changed and the better way to do it now. I prefer to jump in later when things are more mature and I can learn the most stable and liked way of doing something, instead of having to relearn the same thing multiple times as it changes.
Inspired by this blog post by Noel Berry, I started playing with SDL3 and C# yesterday, experimenting with falling sand algorithms (implemented sand, stone, and water) https://github.com/alvivar/falling-sand
Agreed. I rarely find the guardrails of plan to be necessary; I basically never use it on opencode. I have some custom commands I use to ask for plan making, discussion.
As for subagents, Pi has sessions. And it has a full session tree & forking. This is one of my favorite things, in all harnesses: build the thing with half the context, then keep using that as a checkpoint, doing new work, from that same branch point. It means still having a very usable lengthy context window but having good fundamental project knowledge loaded.
There a lot of plugins to handle 2D (2.5D) games on Unity, I am currently using 2D Toolkit ($50) for sprites and it's awesome. I also recommend to check RageSpline and RagePixel, this tools provide features totally integrated with the IDE and really easy to use.
I haven't try CoronaSDK but I can see a lot a potential in 2D games with Unity, not just 3D. I fact, you can see a lot of nice 2D games in his showcase, for example Zombieville USA and Max & The Magic Marker.
What about Central America? I guess we are few in HN, but if it's not part of poll, we never know :( This happen in almost all the demographics polls here...
Indeed. We, central, are always "merged" into south america or Mexico depending on who you ask. I don't blame them though since in recent centuries we have not been a major world player.
Maybe some people have already reached that point after so much AI coding and are now warning us; they pushed so hard that they understand the limits. But this is the kind of thing you need to experience on your own.
You need to experiment, learn, test the limits, think for yourself, take as many steps back as you need.