a backdoored claude code extension build (2.1.313) shipped through an editor marketplace and dropped a persistent ssh backdoor. a coding agent's extension holds the shell, the repo and the ssh keys on every laptop that installed it, so editor extensions belong in the same inventory and version pinning policy as packages.
nitter.cf/PhorionTech/status/211…
i was halfway through designing a calling api for ai agents. mcp tools, direct sip to openai, cloudflare for orchestration, prepaid billing, structured results.
then grok announced calling. guess i'm shelving that one.
Grok @Bot can now call someone or a business for you, make a request on your behalf, take notes on the response and send you a note summarizing the conversation!
been running mythos 5.1 for code scanning. ran claude 4.6 on the same repos.
same findings. 4.6 just flagged more false positives.
starting to wonder what the price gap is actually buying me
dated call, oct 24 2026:
this week it was php2shell, a Brotli RCE, and a GitLab bug dating back to 2014. at least two of them were found by models.
finding bugs is no longer the bottleneck. by oct 2027 the real limit on every security team is how many changes prod can absorb in a week.
checking back on this in a year.
Codex measures the remaining
Grok measures the used
Same quota, opposite math. Why are we like this 😅
Tried out GPT Live,
Here are my thoughts: I see no difference they current voice models today, if anything I found it a little slower and sluggish. I only did try the trivia function.
I’ll go back in a few and try out the conversation function
OpenCode seems to have badly underestimated my Astra Pro usage.
OpenRouter ended up reporting roughly 3x the cost OpenCode showed me.
Has anyone else run into this? Is OpenCode miscalculating token usage/cost, or is there another reason for the gap?
