This result has been previously established:
- teapaw.org/alessio_joseph/status/…
- teapaw.org/benswerd/status/211983…
2
27
D. Bohdan retweeted
Base models are super useful for deep understanding of LMs, and what originates in pre-training vs post-training. But experimenting with large base models can be hard, annoying or costly for individual researchers.
That’s why we’ve built a platform that gives free access to base models for researchers and tinkerers working in LLM psychology. Currently serving Llama 3.1 8B, 405B, and Trinity-Large-TrueBase
1/3
D. Bohdan retweeted
for the past few months i've been asking our models to paint. opus 5.5 is very skilled at emulating different styles
every image here is a python program generated pixel by pixel. there is no image model, and no off-the-shelf art software. instead, it's about 7,500 lines of code using standard libraries to emulate different brush styles. the agents don't use any pictures as reference, instead working only from what they know about each painter
Credits
Footage: FLUX 3 Preview, @bfl_ai.
Prompt orchestration: Hermes Agent running GLM-5.2, @NousResearch.
Concept, story, and shot scripts: Claude Opus 5 across several parallel sessions.
Additional brainstorming: GLM-5.2 and Kimi K3.
Directed and corrected by me.
127
D. Bohdan retweeted
intruders will be trapped in an infinite labyrinth of hallways until they forget why they broke in
en.wiktionary.org/wiki/math#… In old Ireland, a math problem attacks you
1
27
Claude Opus 4.8, Nano Banana Pro. Transcript: claude.ai/share/39553527-4c2….
52





















