This means that agentic coding isn't exactly a replacement for software engineering. It is a fundamentally different way of producing software, with different best practices and different use cases. Just like ML.
SOFTWARE
-
Agentic coding as machine learning
By
–
Agentic coding is a form of machine learning. Generated code is best treated as a blackbox artifact whose behavior and generalization should be managed via empirical evaluation, like with any ML model.
-
Codex Automates Expense Reimbursements
By
–
Codex quite literally filed my reimbursements, downloaded invoices since the start of the month, updated the expenses spreadsheet and filled the actual form all by itself Used Drive & Sheets plugin for state tracking
Gmail plugin for tracking invoices
Chrome extension for actual -
DeepSeek v4 Flash Impresses Locally
By
–
OPEN SOURCE AI is killing it. DeepSeek v4 Flash is a quasi-frontier model with a massive 1M context window. It can LOCALLY on a 128GB Mac using specialized 2-bit quantization. Asked my OpenClaw Engineering Agent Ross about the model and he's impressed.
-
Using AI tools to generate a pre-game podcast
By
–
having codex + claude make a pre-game podcast for me before my writing session today lol
-
Open-Sourced Sparse Training Code for H100 GPUs
By
–
For those interested in the implementation details, we’ve open-sourced the reference code for this paper. The repository includes our sparse training code and the custom CUDA kernels designed for H100 GPUs leveraging the TwELL packing format. GitHub:
-
Google CodeWiki: AI Explains Code and Generates Diagrams
By
–
🚨Google lanzó CodeWiki y convierte código imposible en explicaciones simples.
— Nico (@nicos_ai) 9 mai 2026
Pegas cualquier repositorio y la IA lo convierte automáticamente en una documentación interactiva.
No solo resume el código:
• Genera diagramas automáticamente
• Explica cómo funciona cada parte… pic.twitter.com/A6KyXtlmB1Google launched CodeWiki and turns impossible code into simple explanations. You paste any repository and the AI automatically turns it into interactive documentation. It doesn't just summarize the code: • Generates diagrams automatically
• Explains how each part works
• -
Peekaboo 3.0: Major macOS Update Released
By
–
Peekaboo 3.0 is live. Biggest release since 2.0. Action-first macOS computer use Unified screenshot + UI detection Cleaner JSON across CLI + MCP Better snapshots I started this last year, but the models just weren’t good enough. Now they are.
-
Debugging with Ephemeral Crabbox Sessions
By
–
Whenever I investigate a bug, I let codex recreate the exact state in an emphemeral crabbox, verify the bug, fix it, verify the fix. No messy state because local system might be polluted, and no slowdown because I run 10 sessions in parallel. http://
crabbox.sh -
Lighter and Faster Language Models
By
–
Sparser, Faster, Lighter Transformer-Based Language Models Paper: