Prosthodontist & Clinical Demonstrator 🦷 | Fusing clinical dentistry with code to advance surgical precision & AR guidance. gaming & anime off the clock
@GrokInsider@bot@XDevelopers I have raised tickets since yesterday regarding a couple of bugs , would appreciate solving them
And i keep sayiing u guys nailed it great job 👏🏼
I have raised tickets to certain bugs 24 hours ago havent been resolved yet , also great product u nailed it with this one .
I burned yesterday 100 million tokens most of them figuering out whats wrong before raising a ticket .
A cool feature would be grouping the bots in the side panel
Alao the clicks on the screen is a bit slow 3 mins for a click .
Also a good plan for future users a starter pack of scertian bots related to which ever idea or inteoduction whenever using the bot
Last thing would be a token meter yesterday grok wasnt been able to read the usage at all or tge tokens we spent on every project , also cant read cursor usage nor his .
I would love to be able to manage the rest after the tickets are resolved as everything is postponed till its resolved .
If i wanna Summerize the bot experience in one word would be ‘’ addicting ‘’ .
Great job everyone u nailed it again.
@tibor_tee Well ,for 4 hours now everything is bad
i had like 4 bugs so far and screenshotted and filed tickets nth is fixed , i lost tokens on looops in agents trying to fix a bug in the chat itself . @SpaceXAI
@benjitaylor The spam accounts of their GitHub’s repos that are filled with prompt injections sometimes ppl posts reaching 400k+ filled with agents injections .
They just made it. And its booming . I wonder how .
i've been building some smaller apps over the last weeks for myself, friends and family and discovered a pretty nice pattern in the process
you see, after building, i'm not particularly interested in fixing bugs or triaging feature requests. i just want to get the job done
so i've set up a system that lets me and other users fix bugs and build features without me having to actually open cursor
the flow:
1. someone files feedback in the app
2. it lands in posthog with the submitted text, session replay, events, and errors
3. a cursor cloud agent picks it up with that context, plus live read-only posthog mcp
4. it loops until the fix is verified, then opens a github pr with tests
5. i get a ping and review it on my phone
we give our cloud agents access to all the necessary user context, and they'll figure it out
with this in place, we can start setting up more abstractions in between. if we're getting a high volume, we might want to triage first with another cloud agent or some automation. the feedback can create a github or linear issue, which we later pick up with a cron-backed cloud agent that decides which are duplicates. there are so many ways to configure this, you just gotta try it out and see what works for you
but there's so much more here that is untapped. with session replays and event logs, you can have a cloud agent look at each session replay to extract ux pitfalls and improvement areas. you can have another agent looking at event logs to see weird patterns. another one for errors or similar
try it out and see what you can do!
@nikitabier Btw no one noticed , but great job on banning the “pedos”account “sthey used to spam replies with telegram accounts .
i reported over 100 of them .
Your latest update cut 100 but yesterday some of them came up with a new strategy using unique hashtags to mimic a community .
- متاحة لمشتركي Pro وMax وTeam، مش متاحة على Enterprise
- ملاحظة خصوصية: الـ screenshots بترسل لأنثروبيك وبتتخزن حسب إعدادات الاحتفاظ العادية، فبينصحوا متسجّلش دخول بحسابات حقيقية على الجهاز اللي Claude بيتحكم فيه
يعني اللي ظاهر في الصورة (Claude بيفتح simulator، بيثبت togi-app، وبيتفاعل معاه) واقعي ومطابق للفيتشر الجديد فعلاً، مش فبركة.
Anthropoc 🛑
أطلقت الأسبوع ده (public beta) ميزة اسمها iOS Simulator pane في Claude Code Desktop على الماك.
باختصار:
- Claude Code بيقدر يفتح ويشغّل ويتحكم في iOS Simulator بتاع Apple مباشرة (تثبيت، تشغيل، تصفح التطبيق، قراءة الشاشة)
(1)