juliangoldsmith

Impulse control issues, like ADHD, can factor in too.

A possible "third variable" could be intelligence. It's been shown to be strongly correlated with success in general, and it seems likely people of similar intelligence would find it easier to relate to each other.

The claim isn't so wild when it's a generalist versus a finetune trained specifically on the tasks being benchmarked.

That benchmark ranks Kimi K2.6 and K2.7 Code near the bottom. Both are below Ornith 35B. It ranks Gemma 4 26B much higher than GLM-5.2. The results don't make much sense.

It looks like they're comparing Orinth 9B to Qwen 3.5 35B, not Qwen 3.6. I guess it kind of makes sense since it's a finetune of 3.5, but I totally missed until I looked closely.

In my brief tests, Ornith 35B performed quite well. It won't replace DeepSeek V4 Flash for me, but if it was fast and cheap enough it might.

I don't remember being super impressed with Ornith 9B, but I could see it being on par with Qwen 3.5 35B.

It should improve agents' action selection by allowing them to evaluate actions' effects before performing them.

An agent using only a regular LLM has no real way to predict the results of its actions. It has to just take an action based on its training data and hope it's the right one. With a world model like this, it could do a second pass before each action to catch mistakes.

I don't know if this actually delivers yet, but if it does it might help make agents more usable.

One can only imagine how much money Intel would have made from Optane during the ongoing RAM shortages. It would be absolutely perfect for warm KV cache, and potentially good for MoE expert offloading.

No true Scotsman would ever use binary blobs.

Blocking by age rating takes out the majority of the classic Disney movies and shows. They only consider the newer CGI stuff "child-friendly".

The silenced errors aren't guaranteed to be memory leaks or use after frees. There are some situations where memory is being handled properly, but the borrow checker isn't able to prove it.

One example might be a tree-like struct where a parent and child have references to each other. Even if everything is cleaned up properly, the borrow checker has no way to know that when the struct is created. Solving it requires unsafe at some point, usually through something like RefCell.

It sounds like you were stuck between a rock and a hard place there. Hope the Rust integration goes well.

>trading off for speed

If speed is a concern, why did you all stick with Synapse (essentially single-threaded due to the GIL) over moving to Dendrite? As far as I can tell, Dendrite is, for all intents and purposes, abandoned.

It doesn't appear to be open source, so users have no control or lasting guarantees of privacy.

As someone who as attempted to use React Native for Windows, I can tell you that the "native" XAML doesn't make things any better. If it was using web technologies I wouldn't need to manually modify RNSVG to fix segfaults when an SVG goes offscreen.