Made the previously paid article "Becoming a better writer" free. I see too many devs writing low quality slop with AI. Hopefully this helps those of you who want to share more of your own experiences, using your own words - we need more of these! newsletter.pragmaticengineer.com/p/becoming-a...

Show Post

I actually think Azmi Bishara describes this process of ideological replication and convergence really well in his 2021 book

Show Post

This is good advice from the Claude Code team (posted on X) for how to think about working with models like Opus 5.5. I would add: build checkpoints where the model reports back to you with interim ideas or prototypes so you can guide & give feedback, rather than one-shotting on your goal.

Show Post

CPython now has a couple of labels to help us handle low-quality AI contributions. If we add "AI-needs-explanation": a bot asks the author to explain their changes in their own words. "AI-guidelines-not-met" is similar, but also closes it. discuss.python.org/t/updated-tr... #Python #CPython #AI

Show Post

DiffuSpace's Clover-35B-A3B-Preview (open-weight) An open-weight production diffusion language model (dLLM) with 35B total parameters capable of 680 tps on a single card at BF16. Blog: diffuspace.ai/blog/clover-... Repo: github.com/DiffuSpace/C... Model: huggingface.co/Diffuspace/C...

Show Post