Claude Code and Opus 4.8 love to describe changes in comments (perhaps because that’s what’s on its “mind” at the time), like “this used to do A but that did a bad thing so now it does B”. I’ve almost convinced it that changes go in the commit message, not the comments.
Some of this post reminds me of a story I heard long ago from someone who had worked at a HW/SW company. They’d transferred an engineer from the ASIC design team to the OS kernel team, though he’d never been on a software team before. After a while the manager called him in for the following conversation:
Manager: You’re doing amazing work — zero bugs in production! I’d like you to mentor the other SWEs on how to get their bug count down too.
When my friend's kids were totally obsessed with League of Legends, I offered to set up a home firewall with increasingly difficult workarounds, so by the time they graduated high school they'd at least have a cybersecurity certificate and possibly a Ph.D in networking.
No relation. GUID is just a format for a 128-bit unique number, used throughout the software industry. This is a specific 64-bit number assigned to your Windows device.
I thought the point was not that Mythos finds more vulnerabilities, but that it can exploit them much more successfully. I thought the report showed it didn’t find much more than Opus 4.8. (Or did I misread?)
My current technique, which seems to have improved maintainability, is to guide Claude to write commit messages specifically focused on "why this was done", "what changed in the theory of operation", and "what changed in the code". Then just reviewing the commits for a file or dir gives it a ton of useful context distilled from the sessions that produced them. Also, making a docs dir with concise .md files explaining the theory of operation and updating them with every commit.
I often tell Claude Code to look at previous sessions in ~/.claude and it’s happy to jq/grep its way through them with no special tool. But being more efficient is always good.
Apparently, though not very carefully. The "particularly large LLM generated code churn" in the ram library, for example, is the LLM being used to simply git-revert a change that was not originally done by an LLM.
The manifold is in the middle (“small input space is expanded onto a big manifold and contracted again”) so f(manifold) would need to be in the middle too.
Anthropic submitted a long, thoughtful framework proposal, which everyone seems to be ignoring in favor of hot takes like “they asked for this!” No they didn’t, not at all.
Résumé: CMU (Mach, Coda) -> Apple (Newton) -> Microsoft (Windows, IE, MSN, etc.) -> Jackson Fish Market (adorable consumer apps) -> CareZone (helping you manage healthcare) -> Walmart (still healthcare, but bigger) -> Invaio (healthcare for plants)
Send mail to user walter on host waltersmith.us.
http://waltersmith.us/ (if it's not broken)