6h ago · 7 min read · Earlier this year, Boris Cherny, the creator of Claude Code, published a thread on how he and his team use the CLI they built. A dozen tips covering everything from running parallel sessions to slash commands to subagents. The one I kept circling bac...
Join discussion7h ago · 10 min read · The hard part of building a presentation is figuring out the story. What are you trying to say? What’s the structure? Which sections build on which? Where does the data go, table or bullets? Before th
Join discussion
19h ago · 5 min read · LangChain released DeepAgents this month and it's already at 15,000 GitHub stars. The README says it was "primarily inspired by Claude Code, and initially was largely an attempt to see what made Claude Code general purpose." So let's compare them. An...
Join discussion1d ago · 5 min read · You can review an AI diff with three models and still have zero ground truth. They'll tell you what looks "reasonable", not what's correct. The failure mode isn't "bad code". It's unfalsifiable intent: the requirement never became something you can r...
Join discussion2d ago · 4 min read · Introduction I've been testing Ralph loops recently for agentic coding. The idea is simple: spin up new Claude Code sessions for each task to get a fresh context until the agent achieves the goal, and
Join discussion
2d ago · 3 min read · Claude Code lets you customize the status line at the bottom of your terminal. The default suggestion is a bash script, which works but gets clunky fast and difficult to maintain for more complex features. There are other tools out there that solve t...
Join discussion2d ago · 6 min read · The morning digest surfaced Leanstral -- Mistral's open-source agent for formal verification in Lean 4. A mixture-of-experts model (119B total, 6.5B active per token) that scores within 80% of Claude Opus on the FLTEval theorem-proving benchmark at a...
Join discussion2d ago · 3 min read · A YouTube video titled "Claude Code + Autoresearch = SELF-IMPROVING AI" went viral four days ago. It shows Karpathy's autoresearch repo connected to Claude Code, generating research loops that improve their own outputs iteratively. The comments secti...
Join discussion3d ago · 9 min read · There's a rule every engineering team learns early: the person who writes the code does not review it alone. It seems obvious once you've shipped a few bugs that your own brain was too close to see. T
Join discussion
