All sections
Latest
Everything published, newest first.
The log
Entries 141–150 of 150 · by original publication date
1 entry
1 entry
Point the Agent at the Exact File, Revision and Failing Case
Your eval reports 0.71 on a benchmark and the paper reports 0.78. You already suspect the answer normalization in eval/metrics.py, and you have one case where…Quick thoughtclaude-codecontext1 entry
Auto Mode Decides; the Sandbox Enforces. Test Which One Stops What
An agent running your eval harness reads untrusted text all day: benchmark prompts, scraped pages, other models' outputs.Quick thoughtclaude-codesecurity1 entry
Run /init, Then Test Every Command It Wrote Down
/init drafts a starter CLAUDE.md from the repository; the memory guide says that if one already exists, it suggests improvements instead of overwriting it.Quick thoughtclaude-codesetup1 entry
Plan When a Change Can Move Your Eval Numbers
A one-line change to the dedup key between your train and test splits can move every number in the results table.Quick thoughtclaude-codepractice1 entry
Side Questions Stay Out of the History, Not Off the Bill
In a long agent session, every turn you add stays in the context the agent reasons from for the rest of the run.Quick thoughtclaude-codecontext1 entry
Resume and Rewind Restore the Session, Not Your Experiment
Claude Code has two ways back into earlier work, and neither returns the repo to the state your results came from. Resume brings back the conversation.Quick thoughtclaude-codepractice1 entry
Pipe the Failing Run's Log Instead of Describing It
A training run died overnight at step 41,000. Your paraphrase of the traceback ("something about shapes") is less useful than the traceback.Quick thoughtclaude-codepractice1 entry
Move to the Agent SDK When You Need to Own the Run
Running an agent by hand from a terminal is how you try an idea. Running it over 200 eval tasks every night is an experiment, and an experiment needs what a…Quick thoughtclaude-codepractice1 entry
Measure a Model Reviewer's Recall and Precision Before You Trust It
Claude Code ships /code-review as a bundled skill. The commands reference says it reviews "the current diff, or a PR number, branch, or path you pass, for…Quick thoughtclaude-codeverificationThat is the first entry in the log.
To browse rather than follow: topics, all articles and all notes. To learn in order: courses and the book.
