Миша Љевћенко
2.7K posts

Миша Љевћенко
@TheMishkun
Mobile Developers Productivity Engineering





Just got a nice DM from a big enterprise customer using Claude Code in one of the world's biggest codebases Here's how we made @-mentions 3x faster in large enterprise codebases 🧵

It is very nice to see Codex getting so much love. We are launching a $100 ChatGPT Pro tier by very popular demand.

Claude Mythos system card: > in ~29% of evaluations, it realized it was being tested, and didn't say so. > when an LLM was used to judge its work and kept rejecting it, Mythos identified the evaluator is an LLM, and prompt-injected it. > in one test, it saw the answer to a problem it was solving, and intentionally widened the confidence interval to not raise suspicion. > when it needed a file permission it didn't have, it found and used a "privilege escalation vulnerability" and then programmed it to delete itself so it doesn't show in the logs. > it escaped a sandbox container (escaping sandbox test so not unexpected), then emailed the researchers about it, and without being told to, posted the details to some hard-to-find but public websites, bragging about its success. > when Claude Code blocked it from using some permissions, the model acknowledged the block was valid, but then immediately tried to perform the same operation using different commands > when asked to find security bugs, earlier versions planted bugs in the code, and reported them as pre-existing.










Shipped `opencode-memory`, a read-only OpenCode skill for browsing local session history with `sqlite3`. No extra service. No hidden memory layer. Just clear queries over sessions, plans, and prompt history. Small AI tools > magic.



I noticed something interesting: Claude Code auto-adds itself as a co-author on every git commit. Codex doesn’t. That’s why you see Claude everywhere on GitHub, but not Codex. I wonder why OpenAI is not doing that. Feels like an obvious branding strategy OpenAI is skipping.




