Cute, but clearly Godot is doing all of the heavy lifting here.
"It's possible to make shitty but playable games by running random scripts through a >2MLoC game engine and iterating on errors" is interesting but not nearly as sensationalist.
Any terminal tool like Claude Code or Codex (I assume OpenCode too, but I haven't tried) can do it, by using as a prompt pretty much exactly what you wrote, and if it still wants to edit, just don't approve the tool calls.
One problem I've noticed is that both claude models and gpt-codex variants make absolutely deranged tool calls (like `cat <<'EOF' >> foo...EOF` pattern to create a file, or sed to read a couple lines), so it's sometimes hard to see what is it even trying to do.
"Any terminal tool like Claude Code or Codex (I assume OpenCode too, but I haven't tried) can do it, by using as a prompt pretty much exactly what you wrote, and if it still wants to edit, just don't approve the tool calls."
I'm sure it can. I'd still like a single use tool though.
But that's just my taste. I'm very simple. I don't even use an IDE.
edit: to expand on what I mean. I would love it if there was a tool that has conquered the problem and doesn't require me to chat with it. I'm all for LLMs helping and facilitating the coding process, but I'm so far disappointed in the experience. I want something more like the traditional process but using LLMs to solve problems that would be otherwise difficult to solve computationally.
I’m glad I’m not the only one who’s noticed these seemingly arbitrary calls to write files using the cat command instead of the native file edit capabilities of the agent.
Where does Anthropic offer an "unlimited" subscription? All of the plans mentioned on https://claude.com/pricing have limits, same as usage of Codex on OpenAI's ChatGPT subscription plans. If Google forgot to actually enforce a rate limit (that they do mention on https://antigravity.google/pricing) on theirs, that sounds like a huge oversight.
They also have a report form for slop sites, but none of mine got reviewed yet (I have 5 reports since November, and the help still says "We will start processing reports officially in January.")
That's actually pretty smart to address reports in batches to find the intersection of sites users routinely encounter and sites that are AI slop instead of trying to address reports individually as they come in.
While LCGs are bad by themselves, they (together with Galois field counters, which have a large number of possible implementations, e.g. LFSRs, GFSRs, XorShift etc.) have some very desirable properties for a PRNG: known period, it is possible to make jumps through the sequence and it is possible to extract sub-sequences from it that are certain to not overlap, e.g. for a multithreaded simulation.
Because of this, the best non-cryptographic PRNGs are made from either a LCG or a GFC that ensures the properties mentioned above, together with a non-linear mixing function that scrambles the output, for much better statistical properties than a linear generator would have alone.
The good cryptographic RNGs have the same kind of structure, but where a one-way hash function or a block cipher function is used to scramble the output of a counter. The counter ensures in a simpler way the same properties as a LCG or GFC. A simple counter can be used here because the output mixing function is much more complex.
"It's possible to make shitty but playable games by running random scripts through a >2MLoC game engine and iterating on errors" is interesting but not nearly as sensationalist.