Viewing profile — YuechenLi

Sure, what I mean by that is that LLM makes different kind of mistakes than humans, they usually take the shortest direct route to accomplish their task. You can see that with the …

C#, only because of dotnet ecosystem and tooling is great. TypeScript is a dark horse candidate, it's a great language with a great ecosystem trapped by JS tooling, and most of all…

I wouldn't say Go is IDEAL for AI coding, but it certainly has the case for one of the best programming languages that currently AI uses. Go definitely has its share of problems fo…

Nvidia's biggest advantage in AI has never been only their hardware performance but how entrenched their software is in ML research that flowed down stream. However, if you've actu…

If you actually read the data, especially the distribution graph in the last image, the conclusion that it draws is "the run-to-run distribution variance is so big that there doesn…

Reflection is good for prototyping and get something setup quickly, but if you build your architecture around it, not only do you lose access to NativeAOT, the code becomes very ha…

Go is absolutely one of the best programming languages for LLMs for the reason you say, and Python is just what LLMs like to use to write short throwaway scripts. Frontier LLMs are…

>But a genuinely good steak, medium-rare from edge to edge, browned properly, seasoned right, consistently delicious, is a different matter entirely. Actually it's pretty easy to g…

Cobol code isn't esoteric, but it is designed in a way that is unambiguous and clear about its control flow, but very verbose and tedious to read/write. Translating from Cobol to a…

10Hz is still a 0.1s of latency, which doesn't seem like a lot until you realize that an Arduino typically runs at 16 Mhz, which is literally a million times faster than running a …

Running a full LLM to actuate a robot is way too heavy, the minimum latency they can get down to is probably 1-2 seconds even with powerful GPUs, which is not very useful for pract…

Not always. If an instruction is short and vague, then LLMs tend to fill in the blanks by guessing and the results are unpredictable. Semantic density is the key, prompts/instructi…

LLMs don't really read documents like parsers do, from what I've observed, they behave like they first skim the document and find the section that they think are relevant to their …

[flagged]

Yeah, I still don't understand why they don't just use enums and have to invent a special "union" keyword instead. C#'s enums are extremely underpowered to begin with and the synta…

So... the verbosity of Go without the compile speed of Go? Go is not a language I would associate with ergonomics, and this doesn't even have most of modern C#'s best features: doe…

I got tired of Codex/Claude not being able to write good UI reliably, so I made a TypeScript library toolbox to help with that. https://github.com/yuechen-li-dev/MachinaLayout.JS P…

Just personal experience, I just find it way easier to do frontend work with Claude than it is with Codex.

The answer is it depends. Claude's generally better at frontend and debugging tasks, while Codex is stronger at backend features and exploratory work. They have very different codi…

Fair point, I phrased that too broadly, and you are right about the loose correlation. What I was gesturing at, badly, was more that Zig’s low-abstraction / explicit-by-default syn…

>Combined with the Rust rewrite, ICU changes, and identical code folding, Bun's binary size shrinks by ~20% on Linux & Windows. People who are surprised by this probably has not se…

I'm sure you know that JSON are object literals in TypeScript, there isn't really even a serialization process that's needed there. The AST/IR can still be in JSON, but the authori…

>Instead of requiring verbose low-level parameters such as scales, axes, spacing, and layout. Ok, Microsoft is conflating two different things here: LLMs don't really care about co…

I mean, the key is to stop trying to one-shot everything: The main problem I found with LLM code is more that they always try to take the shortest path to the solution possible, so…

Yeah, one of the big problems with that is that Claude/ChatGPT doesn't perceive images the way humans do at all, so when you upload an image to them, it gets tokenized in some form…