Yeah I mean I also chuckle at good (or cheap) puns sometimes. But wordplay and puns are the current ceiling of LLMs. Good at them because they're purely structural (pattern-match on phonetics, then swap the meaning). In that bit, there's no buildup, no callbacks, no escalation, no expectations to subvert, no thesis, no perspective.
Grounded, buried, couchy, deep-seated, eyes, baked... It's like a thesaurus!
I feel like human comedians would have to deal with a lot of layered subtleties. They would make the potatoes _serve the bit_ instead of _be the bit_.
I'm not sure if this is mythos-specific though. Past models have been great at puns! They do wordplay and puns reasonably well because those are structural.
However, the concepts of comedic timing, subversion of expectations, and emotional punch are kinda contrary to how LLMs work. LLMs are trained to minimize cross-entropy loss. So by construction, they're biased toward the statistically expected.
> Everyone says that but I don't see anyone cooking up the next photoshop and selling it at $3/month.
Yup, same reason you can't throw manpower at a software project and expect a proportional outcome (Brooks's Law). AI amplifies what's already there; it doesn't conjure taste or product vision out of thin air.
Yeah to me, Burst+Jobs and Compute shaders are so easy to work with in Unity, I haven't felt the need to squeeze more perf out of C# in a long time.
For modding and OTA stuff I just use a scripting language with good interop (I made OneJS partially for this purpose). No more AOT issue and no more waiting for domain reload, etc.
Yup, I agree with the author 100%. By far the worst part of AI code generation is the inability to discern old and deprecated APIs/syntax/workflows of tech stacks that are constantly changing.
As someone who maintains multiple JS libs and provides support on Discord, the #1 reason I default to using TW is because it lets me drop code snippets in chat without lugging around an extra CSS file or walls of inline styles, keeping everything compact and easy to read (tons of vertical space saved).
Without TW, that snippet may need to take 3x more lines.
---
My major issue with TW at the moment is that I use TW in a non-browser environment (Unity), so TW3 is fine since I can tweak everything with JavaScript. TW4 shifts everything to CSS, gives zero workarounds, and my setup crumbles.
This was many years ago, after Unity released mathematics and burst. I was porting (part of) my CPU toy pathtracer to a compute shader. At one point, I literally just copy-pasted chunks of my CPU code straight into an HLSL file, fully expecting it to throw some syntax errors or need tweaks. But nope. It ran perfectly, no changes needed. It felt kinda magical and made me realize I could actually debug stuff on the CPU first, then move it over to the GPU with almost zero hassle.
For folks who don't know: Unity.Mathematics is a package that ships a low-level math library whose types (`float2`, `float3`, `float4`, `int4x4`, etc.) are a 1-to-1 mirror of HLSL's built-in vector and matrix types. Because the syntax, swizzling, and operators are identical, any pure-math function you write in C# compiles under Burst to SIMD-friendly machine code on the CPU and can be dropped into a `.hlsl` file with almost zero edits for the GPU.