Dr. Umer Farooq

@ehtelad6 It’s clear now but it was a mess from 8 am till 9:30 am. Many O level students going to expo or Karsaz for their exam got late. Pathetic state of affairs.

Avoid university road from Nipa to bait ul mukkarram masjid

@mreflow I didn’t run OpenClaw but I faced a kind of similar issue with my custom made skill (for business), used Claude, in the beginning so I kept on refining it and kept making it air-tight and now I use the same workflow in Codex and Gemini and it works perfectly.

I don't know if this is a skill issue or something... But I've been playing with OpenClaw a ton for the past 4ish months. I feel like lately I'm spending more time troubleshooting issues with it and telling it what it's doing wrong than I am actually getting valuable use from it.

@claudeai 5 hours limit reset 1:48 am - requested to continue - limit reached 1:49 am, how is this even possible?

Thrilled to support the education GOAT as he reinvents education (again).

Firstly, best brain? who will decide? On the most benchmarks GPT 5.5 has outperformed Claude, if that's what we take into account. 2nd-ly what is the point of having best brain if they don't have the compute power to offer? If we compare 20$ Claude and Codex plan, Codex definately wins due to rate limits. Claude's 20$ plan times out for 5 hours after running a simple skill 2-3 times.

@sama Why are you guys pushing codex so hard? @sama don’t get me wrong I also use and love codex as a worker but opus is the best brain and I bet it will always be, because that’s their focus.

codex with the $20 plan is a really good deal

@EndWokeness @grok is it true that 10 million + illegal immigrants entered Europe from 2000 till 2026?

Each. Dot. Represents. 100. Migrants. This is what an invasion looks like:

@IntCyberDigest They didn't used Mythos to scan their own access vulnerabilities?

🚨 Unauthorized users have had access to Anthropic's closed model 'Mythos,' capable of finding vulnerabilities across every system and software. The users were part of a Discord group hunting for unreleased models.

Is this man really the PM of Pakistan? 🇵🇰 In February 2024, Imran Khan won 180 seats from all over Pakistan and Shahbaz Sharif won only 17 seats, yet he got “elected.”

@wayneb @bcherny I guess it is distilled version of Mythos but now sure

@bcherny How much of Mythos made it into Opus 4.7? Don't worry, I won't tell

Dogfooding Opus 4.7 the last few weeks, I've been feeling incredibly productive. Sharing a few tips to get more out of 4.7 🧵

@Conor_D_Dart @trq212 I would like to test how it performs at effort medium.

@dr_umerfaroq @trq212 just careful using xhigh, it used my max x5 plan in around 5 prompts i was shocked

Opus 4.7 is a model I’ve loved working with in Claude Code. It’s more agentic and instruction following but also incredibly smart and creative. I think it takes a slight adjustment to get used to, but it's so good with auto mode.

@bramvera @trq212 Try updating CC to v2.1.111 and it should be there in models

@dr_umerfaroq @trq212 same boat, no 4.7 on cc cli

@Conor_D_Dart @trq212 Thanks, just updated CC to version v2.1.111 and there it was.

@dr_umerfaroq @trq212 its been out on cc since they launched, so a few hours now

@trq212 Looking forward to seeing what's to come 👍🏻

I think "prompting" will keep being an incredibly high-leverage skill, like writing or public speaking. It is the skill of talking to agents, mediated by the harness. My main goal is to grow the bandwidth between humans and agents, to help us understand each other better.

@trq212 Count me in, using CC for process automation, built dashboard for cases, developed a web-app as well. I am a dentist.

I want to do some streams where I work with non-technical people using Claude Code to figure out how they might be able to improve their process. My feeling is that just a few tips could make a big difference in efficiency. Any mutuals interested?

@bchernyI I was using Opus 4.6 extended thinking with switched on already in the app from a previous task. I had created a presentation from data but want to change three slides now. I wanted to switch to Sonnet 4.6 but I was unable to as upon changing model new chat loaded. When I wrote the prompt to change three slides, the app flickered & got frozen. I had to force quit. When I restarted the app, my prompt was no where to be seen, my weekly usage had gone 20% and session usage 30%. The usage issue is real.

@doamuslims If anything he should be killing is his diet 😂😂

"We are against Islam and we will wipe Islam off this earth. This is our resolve. Those who follow Islam should abandon it as soon as possible." Hindutva priest Anand Swarup released a video threatening to eliminate Islam.

@amasad what about this? Is it true? x.com/Brand/status/2…

From the founder: “Replit is one of my absolute favorite tools to build with”

@lydiahallie Thanks for the update. Appreciate your coming back on this.

Thank you to everyone who spent time sending us feedback and reports. We've investigated and we're sorry this has been a bad experience. Here's what we found:

You need to be on a pro version of Claude to use CLI, this is terminal basically. It costs around 20$ per month or 17$ if you are purchasing yearly subscription. It really what you want to do. Browsing from CLI is basic actually - it can help you build skills that can automate repetative tasks daily.

@dr_umerfaroq How to do that ? Is it free

Playwright + Claude Code = browser use via CLI