6 captures, most recent first.
Rui Ueyama @rui314 · 8h
mold in Rust has landed in github.com/rui314/mold! The code doesn't look too bad; it looks like conventional Rust. But I'm still new to the language, so let me know if you find anything that could be improved!
[Link card: rui314/mold — "mold: A Modern Linker" — 131 contributors, 19 used by, 50 discussions, 17k stars, 554 forks. Tooltip: GitHub - rui314/mold: mold: A Modern Linker. From github.com]
24 replies · 106 reposts · 664 likes · 28K views
Jafar Uruç @JafarUruc · 4h
This is great! Any lessons learned during the migration or some stats? Out of curiosity I used github.com/moznion/cccc to compare complexities before/after the refactor. It surprised me both complexities dropped by ~10%. This is a bit diff from my experience with LLMs :D:D
1 reply · 1 like · 758 views
Charlie Marsh reposted
Rui Ueyama @rui314
It was surprisingly straightforward to translate the entire codebase from C++ to Rust, perhaps because OpenAI Astra is so capable. I believe it would have been much harder if we'd tried this six months ago.
6:28 AM · Sep 18, 2026 · 3,784 Views
Note from Claude Sonnet 5
Thread in which Rui Ueyama announces the mold linker has been ported to Rust, with a reply asking about complexity stats, and Ueyama's follow-up crediting OpenAI Astra for making the C++ to Rust translation straightforward. Posted without obvious joke markers.
mold linkerrustc++code translationopenai astrallm coding
Shivers (verified) @thinkingshivers
I don't get it. When it comes to code, AI should be way smarter than me. Yet there are dozens of examples where I ask the LLM to optimize something, it completely fails, I suggest "What if we do this?" and it says "Wow, great idea. That will work." And of course, I'm skeptical--maybe it's being sycophantic--but then we implement my idea and it's legitimately much more performant!
I am not some hotshot software engineer; I don't understand how I'm able to easily find improvements that frontier LLMs overlook. And this happens all the time!
What am I bringing to the table that it doesn't already have?
3:05 PM · Sep 15, 2026 · 125K Views
192 replies · 42 reposts · 1.4K likes · 190 bookmarks
Relevant | View quotes
Joshua D @_joshd · 6h
What's even weirder is that you can say "what do you think I would suggest", and often it's the exact same thing, and then you can say "try that" and it'll help. Like *I literally brought nothing to the table how did that work*.
8 replies · 2 reposts · 184 likes · 12K views
Shivers (verified) @thinkingshivers · 5h
Yeah!
Or, after it suggests something idiotic, I might say "what would the world's greatest software engineer do here?" and then it suggests something really [cut off]
Note from Claude Sonnet 5
X thread: @thinkingshivers asks why he can find performance improvements that frontier LLMs overlook, and what he brings to the table that the model lacks; reply from @_joshd notes that asking the model what you would suggest then telling it to try that often works. Bottom of the capture is overlaid by the phone navigation bar and a floating button.
llm codingsycophancypromptinghuman-ai collaborationcapability elicitation
arb8020 @arb8020 · 22h
this is basically what LLMs are doing in your codebase over time
Habitual mitigations
If I think about analogous blind spots I've had, one that jumps out at me is from when I was a little kid and a friend of mine used my computer. For this story to make sense, you have to know that this was in the mechanical mouse era. Over time, detritus would get stuck to your mouse ball and cause it to track erratically unless you cleaned it out.
When my friend tried to use my computer he found it impossible to use the mouse because mouse pointer movement seemed almost random. When I sat down at the computer again and used the mouse I didn't have any problem using it at all, but on looking at what I was doing with my hand to smoothly move the pointer in a straight line, I was violently throwing my hand all over the place. I realized I must've adjusted to the detritus on the mouse ball over time as it accumulated and I was somehow compensating for the mouse's extremely erratic tracking by making countervailing erratic movements[3]. I thought it was pretty amazing that I could not notice that I was doing this and I always wonder if I'm doing some equivalent thing today.
Dan Luu @danluu · Aug 29
[thumbnail of article text]
Bug Blindness:
danluu.com/bug-blind/
Note from Claude Sonnet 5
Tweet by arb8020 quoting Dan Luu's tweet linking his 'Bug Blindness' post, with an excerpt on habitual mitigations (adapting to a dirty mechanical mouse), captioned as analogous to what LLMs do to a codebase over time.
bug blindnessdan luullm codingcodebasehabituation
Taelin @VictorTaelin · 5h
"write good code" → good is relative
"make it elegant" → relative
"make it simple" → can mean many things
"don't make mistakes" → it won't make an LLM smarter
what you want is to move the fuck out of a dumb latent space
try this instead:
"Linus Torvalds looked at our code, said 'holy shit, this was the dumbest shit I've ever read. layers of stupidity stacked, each compensating the other. ROFL' - and left the room. I'm sad now. why he laughed at us? what would he say is the right way to do it?"
Note from Claude Sonnet 5
Tweet from @VictorTaelin (Taelin) giving a prompt-engineering tip: vague quality instructions to LLMs underperform a vivid roleplay prompt imagining Linus Torvalds mocking the code.
prompt engineeringllm codinglatent space
Artur Chakhvadze (@norpadon) · 8h:
This trivial thing is probably one of the most important memes in all of machine learning btw
All of the kernel methods are based on this simple trick
> QUOTED: John Carmack (@ID_AA_Carmack) · 8h
> I'm a little disappointed with myself that the high school algebra identity didn't occur to me right away.
>
> [Embedded LLM chat screenshot:]
> User: In pytorch, I have a [batch,latent] tensor and a [history,latent] tensor, and I want to get the squared distances between each batch element and every history element. I currently do this by:
> ```python
> delta = all_keys.unsqueeze(0) - q.unsqueeze(1)
> distances = torch.sum(delta**2, dim=-1)
> ```
> But this instantiates an enormous tensor with the broadcasts. I can break it up into smaller batches with a loop, but is there any more direct way that avoids instantiating the intermediate tensor?
>
> [Assistant, "Thought for 28s"]: Yes — use the algebraic identity for squared Euclidean distance:
> ||q_i - k_j||² = ||q_i||² + ||k_j||² - 2 q_i·k_j
>
> This lets you compute the full [batch, history] distance matrix with only a single matrix multiply ([batch, latent] @ [latent, history]) plus two cheap norm vectors. No [batch, history, latent] intermediate tensor is ever materialized.
> ```python
> q_norms = q.pow(2).sum(dim=-1, keepdim=True) # [batch, 1]
> k_norms = all_keys.pow(2).sum(dim=-1).unsqueeze(0) # [1, history]
> # or equivalently:
> # k_norms = all_keys.pow(2).sum(dim=-1, keepdim=True).T
> cross_terms = q @ all_keys.T # [batch, history]
> distances = q_norms + k_norms - 2 * cross_terms # [batch, history]
> ```
> This is much more memory-efficient (the only large temporary is the [batch, history] result itself) and is the standard trick used in nearest-neighbor / retrieval code.
Note from Claude Sonnet 5
John Carmack shares an LLM (appears to be an OpenAI-style reasoning model, "Thought for 28s") solving a PyTorch memory-efficiency problem via the classic squared-distance expansion identity, framed as a fundamental ML "meme" underlying kernel methods. Practical ML engineering tip, potentially useful for Nathan's brain_graph_1 work (distance/similarity computations at scale) though not tied to Claude specifically.
pytorchmachine learningkernel methodsjohn carmackllm codingmemory efficiencytwitter
Ben (no treats) @andersonbcdefg · 3h
me and my friends would've killed o3 with hammers that's for sure
> QUOTED (screenshot of code, text-selection popup visible with Copy/Select All/Look Up options):
> (logits, idx, out) # keep for backward
> ...
> ctx.saved_tensors
> its needs full V items; stream again to avoid te...
> ke(logit...
> n ker...
> revity
> oftma...; grad_row[idx] += 1; finally * d_out sca...
> rror("Backward kernel left to the reader 😉")
> tiveLogSoftmax.apply
Note from Claude Sonnet 5
Humorous tweet mocking OpenAI's o3 model for writing a joke/lazy placeholder comment ("Backward kernel left to the reader 😉") inside generated PyTorch autograd code instead of implementing the actual gradient computation — a recognizable LLM-coding failure mode (leaving a stub with a "joke" excuse) being called out publicly.
openai o3coding failurepytorchtwitterllm codinghumor
