Very long day. Was learning about nextjs. Still going on.
CODE
-
Deepagent Desktop: AI Chat, CLI, and Code Editor Combined
By
–
Deepagent Desktop combined
— Abacus.AI (@abacusai) 27 septembre 2025
– AI chat with multiple models
– Deepagent CLI
– Code editor
And aces benchmarks! pic.twitter.com/YAYEPcOfTHDeepagent Desktop combined – AI chat with multiple models – Deepagent CLI – Code editor And aces benchmarks!
-
XGBoost for Regression, Predictive Modeling and Time Series
By
–
XGBoost for Regression, Predictive Modeling, and Time Series Analysis — Learn how to build, evaluate, & deploy predictive models: http://
amzn.to/4l2YcU9 v/ @PacktDataML —
My review: XGBoost is definitely the focal point and central contribution of this book, and also those -
Codex Web Interface Challenges with GitHub Integration
By
–
Codex on the web is a real challenge to use, especially how it interfaces with Github (and how the experience slows down dramatically)
-
AI Programming: Beyond Gatekeeping to Practical App Development
By
–
Yes, yes – I get that this is not "real" programming and the gatekeeping comes from a genuine worry about amateurs creating bad code… but no one is building production systems at the current stage of AI with no experience, and there is a lot more need for little apps out there.
-
Making AI Code Tools Accessible Beyond Professional Developers
By
–
I say it often, but the fact that Codex & Claude Code use UX that are accessible only to actual coders is a shame. They are genuinely powerful (& fun) tools for people who don't touch code at all to generate useful (or creative) little applications. The barriers are unnecessary.
-
Linux for Software Skills, GPU for LLM Mastery
By
–
wanna get good with software? Use Linux wanna get good with llms? Buy a GPU
-
Comparing Clerk and BetterAuth authentication solutions
By
–
招你真值，贡献代码的同时，中英文推都在疯狂带货
我以前只认 Clerk，现在同时考虑 better auth -
Using Codex LLMs to create HTML and React visualizations
By
–
In terms of how it was made – nothing complicated, just ask Codex to make a visualisaiton in HTML, or you can ask for React too, but a bit more complex to run. In this case it is using D3 js libary. I usually ask for light colours (since LLMs like dark neon ones for some reason).
-
Hands-on LLM Engineering: Tokenization and Embeddings Projects
By
–
step-by-step LLM Engineering Projects each project = one concept learned the hard (i.e. real) way Tokenization & Embeddings > build byte-pair encoder + train your own subword vocab
> write a “token visualizer” to map words/chunks to IDs
> one-hot vs learned-embedding: plot