FUTURE WORK – describing differences @ZhongRuiqi has some incredible work on methods for describing the difference between two text distributions *in natural language* we could compare outputs of 20b to the 120b model, or LLAMA, or GPT-5…
LLMS
-
Understanding Constant Codeswitching in Language Models
By
–
what are some explanations for constant codeswitching? 1. OpenAI has figured out RL. the models no longer speak english
2. data corruption issues via OCR or synthetic training
3. somehow i forced the model to output too many tokens and they gradually shift out of distribution -

AI Models Generate Creative Screenplay Examples
By
–
there are a small number of creative outputs interspersed throughout here's one example where the model starts writing a sketch for a norwegian screenplay
-
Multilingual Reasoning Chains in Neural Language Models
By
–
what you can't see from the map is many of the chains start in English but slowly descend into Neuralese the reasoning chains happily alternate between Arabic, Russian, Thai, Korean, Chinese, and Ukrainian. then usually make their way back to English (but not always)
-

Model Hallucinates Domino Problem Repeatedly in Token Loop
By
–
and it truly is a tortured model. here the model hallucinates a programming problem about dominos and attempts to solve it, spending over 30,000 tokens in the process completely unprompted, the model generated and tried to solve this domino problem over 5,000 separate times
-

Embedded Generations: AI Model Capabilities in Math and Code
By
–
here's a map of the embedded generations the model loves math and code. i prompt with nothing and yet it always reasons. it just talks about math and code, and mostly in English math – probability, ML, PDEs, topology, diffeq
code – agentic software, competitive programming, -

GPT-OSS Training Data Analysis: Bizarre Results Revealed
By
–
curious about the training data of OpenAI's new gpt-oss models? i was too. so i generated 10M examples from gpt-oss-20b, ran some analysis, and the results were… pretty bizarre time for a deep dive
-
Early Access Review: Honest Thoughts on New AI Model
By
–
I was not paid by OpenAI. I was just given access to the model in advance to try it out and share my honest thoughts. Read my full review (find it in my feed). you’ll see that I’m not 100% happy with the model. But it is really great at some things!
-

GPT-5 Launch: Cost, Speed, Context Impact for Leaders
By
–
GPT-5 launched yesterday. I had early access and here’s what stood out to me, and how I’d be thinking about it as a business leader right now. Three words: Cost. Speed. Context. Cost → Cheaper than o3, way cheaper if you use Nano/Mini. I do not recommend slashing budgets.
-
Sam Altman Announces GPT-4o Return for Plus Subscribers
By
–
Sam Altman just announced a change in policy, GPT-4o will be coming back, at least for Plus ($20/month) users