Viewing profile — wgd

If memory serves the DeepInfra offering is marked as fp4 because that's the native precision of the experts (which are of course the majority of the weights in a MoE model) so they…

There is https://noslopgrenade.com/

It's actually pretty straightforward to recover file-states from conversation history. I accidentally deleted the wrong repo on my machine once and recreated all the lost work from…

You don't hear about them much because their models aren't really competitive. I really wanted to try Trinity Large as a daily-driver in the MiniMax M2 sort of niche but I couldn't…

> DeepSeek and GLM are left out of the tables entirely: we only have rough characters-divided-by-four estimates for them, not real tokenizer counts, and this post is about measured…

Yeah, I originally expected this to be about a cursive variant which could be plotted as a single-valued function or something.

A more accurate title might be "Average University Students Can't Identify Czech AI Poetry". The random-chance performance seen here is reminiscent of the 50-50 nonexpert performan…

At first I thought this excerpt was meant to warn people off without directly alleging AI authorship, but I guess that's less likely since I see you're also the submitter

The current Deepseek V4 Pro is still just their initial preview AFAIK, with the "real" model release rumored to come later this month. GLM-5.2 might be outperforming simply because…

Pangram does work, in the specific sense that when it says something was AI authored it is vanishingly unlikely that it was written by a human (who was not deliberately trying to w…

> The reason that people don't understand why Anthropic wont let the subscription be used with other harnesses Even more specifically, the very fact that people would prefer, if th…

I've read a lot of his other writings so that context might be informing my reading here but it sounds like he's pretty straightforwardly discussing the potential of aluminum foil …

Yes, those ones would be at least a somewhat-plausible simulation of a real scenario people care about: a once-clean codebase that was allowed to become messy by a succession of in…

"agent pipelines that [...] clean a messy [repository]" This feels like a terrible approach, sufficient to condemn the entire study. Apparently half of the "minimal pairs" in this …

Some dishwashers add a simple timer-based heuristic so if you open it for just a few seconds while you lazily grab something the "clean" indicator stays lit.

I've always been amazed at how terrible most frontier LLMs are at compaction given how embarrassingly easy it is to come up with half a dozen different RL training evals which woul…

The problem is that the moment you introduce shared remote hardware there's a slippery slope leading right back down to "just pay an inference host for model tokens". If you're tra…

[dead]

I've got a GLM subscription (mostly because I like supporting open model makers, pretty sure my monthly usage is so low that pay-per-token would be more cost effective), so I gener…

The GLM-5 series is 744B-A40B. This is not a local model for any reasonable definition of local, but it's an open model which means (once they upload the weights in a week or so) t…

Often in MoE models the experts are quantized while the shared portions, being a much smaller part of the network with greater impact, are kept at higher or full precision. Not fam…

Yeah, the evidence feature is so terrible that it actively harms the overall reputation of Pangram. The main "is this AI or human?" classification is done with a machine learning m…

[flagged]

People say "determinism" but I don't think that's actually the property we care about. For instance you could imagine a compiler that makes heavy use of superoptimization with rand…

Yeah I agree this is probably outside of the intended scope of the silent sabotage mechanism, but there are plenty of reports of the "loud" safety classifier misfiring on innocuous…