dcl

I wonder if this is deliberate... When planning all the models seem to have a very good knowledge of methods, but do not seem to be able to make them work. But this could be a property of RL, I believe it's always been quite challenging and finicky.

Will Claude help me with reinforcement learning code for games? Or is that too small-fry for it to refuse? I've been playing around with RL with the new DeepSeek Flash model but it seems to trip up over itself a bit.

Yes, Jon Hamm's character certainly did get the job done. lol

Yep, being able to understand more complex ideas and having frameworks for thinking/abstracting things will always be helpful. Graph theory is a great example.

Remember when <obviously equally detestable but probably far less capable person> from <party> ran for president and had the support of <the mainstream media> to sway voters and elections?

Did some on our internal datasets. It did not beat our AutoARIMA baselines, they are pretty noisy series though. Custom ML models only do a little better.

There's already books... Gad Saad's 'Suicidal Empathy' is one.

The _adversaries_ once again having a good laugh.

Are they very stationary time series with not very changing dynamics over time?

Any benchmarks against AutoARIMA?

Very keen to try this out tonight. What coding harness do people like to use with these models?

couldn't feel the AGI

Just bought a new ASUS 32" OLED with the stripe RGB subpixel pattern... Looks like I'll have be more careful with burn in than I thought.

We had a Pioneer Plasma Elite and played LOTS of PS2/PS3 games on it, we had no burn in as far as I could tell?

This has always been a challenge for PhD students and researchers, it's just far more likely to occur now it seems. Getting scooped doesn't feel good, but it's a signal you've been thinking about things other people care about.

Interesting, I'll have to check this out.

Would be good to see how it compares to the embedding models from https://www.voyageai.com/ for text. I have used these a few times in the past and have found them superior to the Qwen models compared to here.

What harness you use? Have you tested more than 1?

Is it though? I have found it much easier to fit/diagnose/improve simple classifiers on embeddings/hash vectorized features/etc than iterate on prompts, especially true when using the more modern LLM's (like gpt 5.6 Luna) where you can't even set the temperature to get any sense of determinism.

I do note though, that is infinitely easier to 'deploy' a Jev/LLM based solution than a data/model pipeline.

That is indeed reasonable. But you still need a bunch of trusted data to validate the accuracy of Jev.

I've used LLM's to classify things for numerous projects and it's always really hard to beat linear classifier/decision tree over simple embeddings or even the sklearn HashingVectorizer. However, you DO need to trust your validated data, ground truths for this to work - but you should have these anyway to validate a Jev or similar solution.

What is...?

no scroll bar :(

Interesting. I have been asking it to review code from Opus 5 and it found tonnes of issues, Opus agreed with the findings too.

A bunch of PS2 cards had this effect on me. Fifa 2001, Gran Turismo 3, etc.

How have you found Muse Spark 1.3? It doesn't get much mention, despite pretty good benchmarks. I've been using a bit at home and find it quite good, often finding mistakes made by Opus 5.

the smallest problem that cannot fit in a brain would be pretty interesting

What do you think all the PhD's and post-doc students are doing...? It's not called graduate-descent for nothing :p

In the early days of SC2, I remember people using genetric programming to optimize build orders. I remember a slightly unorthodox Zerg Roach Rush which was _really_ fast.

Using AI to catch up on reinforcement advances, trying to 'solve' Gin Rummy. Will move on harder games after that.