Viewing profile — ianberdin

Check out my MacBook SVG benchmark. From my experience, it demonstrates the Real model’s behavior. However, I notice the errors it makes, which are similar to the mistakes made by …

Anyway, only Opus 5 Max and Fable 5 XHigh + Max make a good-looking Mac.

I still believe my bench is superior to Pelican or Karpathy’s. Everyone knows how a MacBook looks. Any missing or incorrect detail will be obvious. However, Pelican or this world c…

Congratulations, Chris! I’ve always been competing with you, and many users came to Playcode from Codepen. In fact, I even offered to buy playcode.io about 9-10 years ago, but you …

[dead]

Fun fact: we also built our cloud platform based on Fly.io’s ideas, but we supercharged it with a custom Rust filesystem. This platform powers full-stack applications for business …

I've heard stories like this before, how one or a few people miraculously coded up an alternative to Node.js. But can you name even one that actually works properly in production? …

I’m pretty sure Opus 5 is adapted to tricks from long reasoning in Kimi K3 and based on original Opus 4.8. It is not fable in any form.

Opus yes, it likes to explain steps and reread files. Fable is not better, it says zero information between steps and then output a summary. A perfect “send - done”.

Pelican svg: https://playcode.io/blog/macbook-svg-benchmark#model-claude-... It creates the MacBook svg way better than 4.8, yet only fable can make it perfect without visual defec…

Fixed. Converted to PNGs for webpage.

We have a little bit different conclusions. Same pelican grid + MacBook Pro in 3D. Also with end cost. https://playcode.io/blog/macbook-svg-benchmark

Pelican svg and a near-perfect 3D MacBook at max effort for $0.16, about a fifth of Fable's price. Fable 5 still wins on detail with no visible errors, but it's close. And this isn…

Our answer to Pelican benchmark: https://playcode.io/blog/macbook-svg-benchmark

Just checked some of your comments. I see you mostly talk about how everything is AI written.

@dang, why is this flagged?

Thank you for the criticism. I heard you. I added a TLDR. I cleaned up many AI constructions. By the way, I tweaked it a bit, compressed it. One way or another, I want to note that…

[flagged]

[flagged]

Well, criticizing is, of course, great. But the reality is that English is not my native language and I dictated most of it with my voice, then processed it with the help of AI, tr…

We've switched the default model in playcode.io among Opus 4.8, Opus 4.6, Sonnet 4.6, and Sonnet 5. I must admit, Opus 4.8 is quite expensive, and the costs accumulate quickly. Opu…