Indeed
Replying to @natashenka @5aelo
Overall, fuzzing and LLMs are complementary approaches. AI has greatly increased the number of vulnerabilities found and fixed in V8, but don’t turn off those fuzzers yet!
FORKFORK DOG retweeted
9/ where it breaks down: proofs are blind where they abstract. I planted a bug in 4 lines the spec summarizes away — writes routed to the wrong order book. every proof stayed green. unit tests caught it instead.
so no, you don't get to delete your tests.
continuing. one solution would be to create a cgroup like `cgroup memory.max=7G` and retry
3 workers and sitting on 7GBs
hey @poteto it seems like grokbot x wiring doesn't wire
`This X account isn't set up yet. Go to https://console .x. com, register and onboard with this same X account, then come back and I'll retry.`
grok does it's own investigations
```You already did console. x. com and a reconnect today. Same 403 after that. So this is not a missing-login problem. Cursor’s X plugin uses Cursor’s shared OAuth app over HTTP. X’s own Cursor docs want your own developer app through a local bridge. Connect goes green anyway, then every tool dies, and the plugin tells agents to keep saying “go set up the account.” That’s the bug.
report from fields: I failed to run inference for Qwen3.8-27B-GGUF on M4 24GB RAM even with 2k context with Metal Insufficient Memory err.
I suppose if close every app it would run a 4-5 tokens/s but that context is upsetting












