Same thing here. I took a picture of some gravel/grass and asked it to show me what it'd look like with tiles. I showed it another part of the property, and asked it to show me what it would look like with a raised lawn. Super impressive to be able to see a cloudy idea in the physical realm like that.
Thank you. There's a demo save to get the full feel of it quickly. There's also a 2D-ASCII and 3D render you can hotswap between. The 3D models are generated with Meshy. The entire game is 'AI slop'. I intentionally did no code reviews to see where that would get me. Some prompts were very specific but other prompts were just 'add a research of your choice'.
This was built using old versions of Codex, Gemini and Claude. I'll probably work on it more soon to try the latest models.
I've run into this before too, when playing single player games if I've had enough of grinding sometimes I like to pull up a memory tool, and see if I can increase the amount of wood and so on.
I never really went further but recently I thought it'd be a good time to learn how to make a basic game trainer that would work every time I opened the game but when I was trying to debug my steps, I would often be told off - leading to me having to explain how it's my friends game or similar excuses!
I'm assuming it's because nobody can just leave something alone. It's always gotta change, it's always gotta be made "better". And it probably generates a lot of marketing, good or bad.
If they leave it alone on what else would they be working on? Not on something in somebody's else department so it's either being layed off or convince the board that each year's iteration on the same things is the next groundbreaking invention.
You're describing the classical dichotomy between progressives and conservatives, a dichotomy which extends far beyond the political sphere to which is usually is applied. Whether it is in the arts, in architecture, in engineering, in design or in software development. UI design in particular seems to attract the type of person who is among the first to pull down Chesterton's fence [1] with no though given about what might be lost by this action.
How strange. I just tried this out and I see two unauthorised subdomains, with one being an actual "spam" website. However, I don't even know how to delete a subdomain that doesn't show up in my domain registrar or cloudflare!
How bizarre. I'm not in the US either - I'm in New Zealand, and have been using Kagi since their beta I think and currently pay for Ultimate, and to me it's a lot faster than Google.
The other day I was using someone else's computer and used Google, and my goodness, the results were just awful and ... bloated?
From what I understand, it's from people using it in their workflows - say, Claude but keep hitting the rate limits, so they have to wait until Claude says "you got 10 messages left until 9pm", so when they hit that, or before they switch to (maybe) ChatGPT manually.
With the router thingy, it keeps a record, so you know every query where you stand, and can switch to another model automatically instead of interrupting workflow?
I may be explaining this very badly, but I think that's one use-case for how these LLM Routers help.
We get rate limited when using Azure's OpenAI API. As a gov contractor working with AI, I have limited means for getting access to frontier LLMs. So routing tools that can fail over to another model can be useful.
