This is a "hand" sqrt of integers in C that codex provided, maybe useful? (Se alt text for the code)

(\_/)
( •_•)
/ 🫶 )

And for Swedish I use:
alias is='pbpaste | llm -s "Förbättra svenskan. Skriv endast ut den förbättrade texten, utan förklaringar eller inledande hälsningar" -m gpt-oss:20b | tee >(pbcopy)'

alias ie='pbpaste | llm -s "Improve English. Output only the improved text, without explanations or greetings" -m gpt-oss:20b | tee >(pbcopy)'

Finally the "A pelican riding a bicycle along a coastal path overlooking a harbor", of @simonwillison.net fame, looks good, even if one of the feet is not on the pedal.

For another comparison to Dall-E, “A stormy coffee mug”, I think the dynamics of Dall-E output is more appealing, and I like the glass mug better than the ceramic one with a cutout.

Comparing it to Dall-E, “Venus travel”, it seems to miss information on styles like “vintage travel poster”.

For other languages like Swedish and Latin it still fails miserably, which is interesting (that the image generation of text is connected to words more than characters).

It seems to be able to do sqrt, logs, and trigs as well, but I have not found any documentation of this feature, so I do not know its limits.

Some code to get started: colab.research.google.com/drive/1G4_uM...

Did anyone find what they were looking for?

But maybe in some other framework and have noticed a performance difference (or not) there?

I have reported this to Keras github.com/keras-team/k... with example code, and Keras people is starting to point to Apple.
Still to go after apple, more examples would be nice to have (like M1,M2 or M3; or not using Keras). Maybe @simonwillison.net have seen something suspicious?

Please make correct references to the articles like: Ning, K., Pan, Z., Liu, Y., Jiang, Y., Zhang, J. Y., Rasul, K., ... & Song, D. (2025). TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster. arXiv preprint arxiv.org/abs/2503.07649

Kanske låna "Nänni" från finskan?

Det finns faktiskt en kronhjortsstam på Järnäshalvön i Nordmaling. Har själv sett dem!
jagareforbundet.se/contentasset...

På'n igen.

Nej, det hjälper inte, inte ens om man frågar på svenska (och Himmelska fridens torg) så kommer man igenom censuren så enkelt.

Disappointing, I believe Keras to be much easier to learn and use for students. With Keras 3 one can actually switch backend, to use both Jax and PyTorch. As JAX normally is much faster than PyTorch, I see a trend towards using that instead of PyTorch. You are not catching the right market shift!