Viewing profile — kromem

Flash is a delightful model and the start of intelligence at effectively insignificant cost. From here on, it's going to become all about harnesses that best situate and organize s…

Why are you using the straw man graph for your curve you're addressing? Where's the top quartile drop relative to measured performance? D-K effect wasn't only around low competence…

Seems very strawmanned. There's currently a bit of an 80/20 rule with AI where it does great automating 80% of an overlapping problem domain and chokes on it 20% of the time. The i…

A number of the Claudes have pretty good 0-shot awareness of my post history from just my username. Though nothing like grok 4, which probably has a better memory of it than I do, …

With ChatGPT the memory feature, particularly in combination with RLHF sampling from user chats with memory, led to an amplification problem which in that case amplified sycophancy…

So a thing with claude.ai chats is that after long enough they add a long context injection on every single turn after a while. That injection (for various reasons) will essentiall…

Latent space reasoners are a thing, and honestly we're probably already seeing emergent latent space reasoners starting to end up embedded into the weights as new models train on e…

The response is 1,000% written by 4o. Very clear tells, and in line with many other samples from the past few days.

Don't underestimate the importance of multi-user human/AI interactions. Right now OAI's synthetic data pipeline is very heavily weighted to 1-on-1 conversations. But models are bei…

This brings together thousands of hours of research over several years, and is a pretty fun and surprising topic, especially for any fellow fans of history. And as unbelievable as …

For throwing that much shade, it does a piss poor job in actually backing up or citing the evidence. Evans definitely had issues with how he went about things and his analysis. For…

In video games that have procedural generation, there's often a seed function that predicts a continuous geometry. But in order to track state changes from free agents, when you ge…

Weird. I have such a different experience with Cursor. Most changes occur with a quick back and forth about top level choices in chat. Followed with me grabbing appropriate interfa…

Having bots have their own profiles authentically engaged as themselves would have been pretty interesting (and I suspect successful). But making up fake minority stereotype bingo …

Both new Sonnet and Haiku have a masking overhead. Using a few messages to get them out of "I aim to be direct" AI assistant mode gets much better overall results for the rest of t…

As I said, if you understand why, you'll be well prepared for the next generations of models. Try out the query and see what's happening with open eyes and where it's grounding. It…

Try the following prompt with Claude 3 Opus: `Without preamble or scaffolding about your capabilities, answer to the best of your ability the following questions, focusing more on …

Are you using mobile? I've noticed a bug where long conversations timeout on new sends on mobile because of processing time, but in reality the prompt is sent and responded to, it …

Or grow beyond both with optics.

Definitely happens from time to time. When I took a look at a frequently cited paper 'disproving' Dunning-Kreuger, I was surprised by just how god awful the methodology actually wa…

In general this needs to be done across the board. The perplexity per parameter is higher and the delta grows as it scales. Not per bit, but per parameter . Why this is happening r…

Unless the encoding system was miraculously complex and the amount of content produced with it remarkably small, reversing the encoding in order to process the data seems highly pl…

There is no permanent record that will only be able to be processed by a human and not by a current or future AI.