Viewing profile — bluecoconut

Very cool! one subtle consistency bug that made it hard for me to interpret when I was clicking around: the small thumbnail plot vs the full plot often (always?) seem to use differ…

For those who like these types of puzzles, i made a benchmark called pencil puzzle bench Testing AI model's ability to solve puzzles like these. https://ppbench.com/ Can play the p…

I've been working on applying LLMs to long-context, verifiable problems over the past year, and today I'm releasing a benchmark of 62,000 pencil puzzles across 94 types (sudoku, no…

Fun read. One upside of the deterministic schemes is they include provenance/lineage. Can literally "trace up" the path the history back to the original ID giver. Kinda has me curi…

I almost feel like this goes opposite to what attention is good at. This would be good at approximating all the places where attention is low / not sharp. Where attention/the expon…

Bytedance is publishing pretty aggressively. Recently, my favorite from them was lumine: https://arxiv.org/abs/2511.08892 Here's their official page: https://seed.bytedance.com/en/…

Previous paper from DeepSeek has mentioned Anna’s Archive. > We cleaned 860K English and 180K Chinese e-books from Anna’s Archive (Anna’s Archive, 2024) alongside millions of K-12 …

After maintaining my own agents library for a while, I’ve switched over to pydantic ai recently. I have some minor nits, but overall it's been working great for me. I’ve especially…

The first time I got off at and heard Komagome's tune I mistakenly thought it was some halloween special because it was late October at the time, and the song felt so distinct and …

Interestingly this one seems it is from before 高輪ゲートウェイ (Takanawa Gateway) station which opened in 2020, but the numbering shows the gap (JY 25 -> JY 27). That led me to looking it…

Not getting around it, just benefiting from parallel compute / huge flops of GPUs. Fundamentally, it's just that prefill compute is itself highly parallel and HBM is just that much…

I was able to get gpt-oss:20b wired up to claude code locally via a thin proxy and ollama. It's fun that it works, but the prefill time makes it feel unusable. (2-3 minutes per too…

I've been working on something very similar as a tool for my own AI research -- though I don't have the success they claim. Mine often plateaus on the optimization metric. I think …

I’ve been using whisky to play Elden ring on my M4 MBP and it’s been great! I love that the Game porting toolkit and wine all work so well. I did have to do some pinning of steam t…

I tried to do this myself about ~1.5 years ago, but ran into issues with capturing state for sockets and open files (which started to show up when using some data science packages,…

I don’t quite understand this - by 30k pages, is this the number of entries in your index? Did you mean 30M? At the 768 4 =30MB, a scan over it and a sort is on the ~100us or faste…

By my estimates, for this single benchmark, this is comparable cost to training a ~70B model from scratch today. Literally from 0 to a GPT-3 scale model for the compute they ran on…

3400 came from counting pixels on the plot. Also its $20 on for the o3-low via the table for the semi-private, which x172 is 3440, also coming in close to the 3400 number

they use some poor language. "High Efficiency" is O3 Low "Low Efficiency" is O3 High They left the "Low efficiency" (O3 High) values as `-` but you can infer them from the plot at …

some other imporant quotes: "Average human off the street: 70-80%. STEM college grad: >95%. Panel of 10 random humans: 99-100%" -@fchollet on X So, considering that the $3400/task …

That's the low-compute mode. In the plot at the top where they score 88%, O3 High (tuned) is ~3.4k

Efficiency is now key. ~=$3400 per single task to meet human performance on this benchmark is a lot. Also it shows the bullets as "ARC-AGI-TUNED", which makes me think they did som…

I like writing to myself / talking to myself... but I'm trying to convert that internal captured thought / language into brand value and useful information in a wider contexts. Goo…

I write for myself a lot, roughly ~5000 words a day in notes, messages to self, etc. I have no problem writing and talking to myself. It's the editing process and formalizing it fo…

Worrying what others think resonates with me a lot. Every few weeks I try to motivate myself to write more online (HN, X, blogs) and consistently get “self sabotage” stuck. (Been g…