TOOLS

Built tools for Claude code transcripts, prefers native feature

By

–

31 May 2026 21h24

Yeah I've built tools for working with those in the past – https://
github.com/simonw/claude-
code-transcripts
… – but I'd much prefer to have a "native" feature for that so I don't have to worry about mine breaking if they change something

→ View original post on X — @dotcsv

Karpathy’s brain ingestion paradigm: A scalable pattern for various applications

By

@dotcsv

–

31 May 2026 21h03

Karpathy's second brain ingestion paradigm, where you have a folder to dump your raw data into and then an agent processes and structures it to add it to a wiki or second brain, is a scalable pattern for so many other applications. In my case, for example, I already had a

Fear of losing key features after automatic updates

By

–

31 May 2026 20h54

I used to let Codex Desktop update itself, now I feel I must resist updates in case they remove key features I depend on!

Transcription, key artifact of coding agents

By

–

31 May 2026 20h53

When you work with coding agents, transcription becomes one of the most significant artifacts of the work you do; I think recording these is just as important (if not more) than maintaining good commit messages and

Disappearance of the Copy as Markdown option in Codex Desktop

By

–

31 May 2026 20h51

I am really upset about this: OpenAI's Codex Desktop had an option 'Copy as Markdown' to export complete chat transcripts, but this feature disappeared in an update a few days ago Really my favorite feature of

→ View original post on X — @ingliguori

AI Agents: Orchestrating Multiple LLMs for Enhanced Capabilities

By

@ingliguori

–

31 May 2026 19h25

AI Agents ≠ single LLM They’re systems of models • General LLMs → reasoning
• Domain LLMs → expertise
• RAG → real-time data
• Tools → actions & automation
• Open-source → control & privacy Real power = orchestration of multiple LLMs Via Giuliano Liguori