Viewing profile — cgorlla

Based on the reception of our last post we took folks' suggestions to run the new official build of V4 Flash and compare it to the preview that was released 5 days apart. The new b…

Every post is actually scanned for LLM content as well.

A typographic Voight-Kampff test is pretty awesome.

[dead]

We discuss this in the writeup. While we expected this result, it is important for there to be data backing the claims, and an experimental setup that mirrors productions tasks is …

We're actually exploring the changes in the model geometry that cause it to comply or not comply with a given policy next, I think visual representations of that behavior would be …

I guess the AI that wrote your comment for you also conflated the SFT step of the target domain with the political prompts, which, in the sentence you quoted, contradicts your orig…

>We plan to test what happens with a Chinese teacher into a Chinese-lineage base like Qwen next. :)

The fact that you literally thought the examples were used in SFT in your last comment ago calls into question the utility of this conversation, notwithstanding the implication tha…

The examples you're talking about are not involved in the training process, so their number is irrelevant. As stated in the post, the goal of this work is to determine whether a te…

You can try it yourself! https://playground.ctgt.ai

This is fixed

This is fixed.

Agreed, we find this to be an interesting reflection of societal values and norms inasmuch LLMs are.

Abliterated models certainly have their uses but they're not the default choice for most users or enterprises, and thus not the versions of those models most would interact with.

Agreed. It's fixed

You can see exactly what prompts we used and the results here: https://github.com/CTGT-Inc/lineage-eval/tree/main/data We found V4 Flash was significantly more censored than the ba…

It's most likely to occur when distilling a Chinese model from a Chinese base. We plan to do compliance geometry analysis in the future to see what is structurally changing in the …

Consider that LLMs are trained on the corpus of the internet, and (simplifying) consequently give the average answer of the internet. If the desired answer of the censorer is contr…

We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 1…