You may have seen headlines about critical vulnerabilities called PHP2Shell affecting websites that run on PHP. Here’s the plain-English version: - If you have a self-hosted WordPress site: This one deserves attention. Check with your hosting provider that your PHP version has been updated to a patched release. - If you use WordPress plugins: Update WordPress, your theme, and all plugins now. Delete any plugins or themes you no longer use. - For every platform: Use a unique password, turn on two-factor authentication where available, and make sure you have a recent backup. The main risk is not that your website will simply “go down”—it’s that an unpatched server could potentially let attackers access files, member information, or connected accounts. Today’s takeaway: If you run your own WordPress site, contact your host today and ask: “Has my site been updated to a patched PHP version for the PHP2Shell vulnerabilities?”

Answer this poll please ⤵️

I've been using the paid version of ChatGPT for some years and with the new 'work' option I find it still does the trick. I don't use it to generate images. It feels like I now hear everywhere that Claude is much better. 𝗜'𝗱 𝗹𝗼𝘃𝗲 𝘁𝗼 𝗵𝗲𝗮𝗿 𝗳𝗿𝗼𝗺 𝗽𝗲𝗼𝗽𝗹𝗲 𝘂𝘀𝗶𝗻𝗴 𝗽𝗮𝗶𝗱 𝘃𝗲𝗿𝘀𝗶𝗼𝗻𝘀 𝘄𝗵𝗮𝘁 𝗱𝗼 𝘆𝗼𝘂 𝗳𝗲𝗲𝗹 𝗖𝗵𝗮𝘁𝗚𝗣𝗧 𝗶𝘀 𝗯𝗲𝘀𝘁 𝗳𝗼𝗿, 𝘄𝗵𝗮𝘁 𝗶𝘀 𝗖𝗹𝗮𝘂𝗱𝗲 𝗯𝗲𝘀𝘁 𝗳𝗼𝗿? Do you need both? My concern is that I move from one to the other, learn how to use it and then suddenly the other is best again. Development is so quick. Before I decide, I really love to find out more about the things where one is clearly stronger than the other...

I built my whole program with 16 GPT assistants and I already started to get nervous August last year, when they suddenly dropped model 40 and replaced it with 5, an unruly, will-just-do-my-own-thing-and-cut-corners model that totally didn't work for my program... 😅😐 luckily they brought it back after the outcry but ever since I was on the lookout for a solution. I found it in Claude skills in January this year and managed to bring it all across just in time before my GPTs became totally useless. But I didn't find the move to skills that straightforward, Claude is very different again, better in some things worse in others. I couldn't just copy things across. But in the end I'm super happy with the skills set up, it can handle complex workflows really well and is super obedient, which is great for my process. It was shocking for me how the rug could just be pulled from under you in the AI world. It was maybe naive of me to think it would be different but I didn't expect functionality to just dissappear, I thought things would just get better, not worse or less advanced. But Open AI and custom GPTs gave me the space and technology to develop my thinking and process so it's all good in the end. With skills you are more the owner of your work and less just renting the space. What has your experience been? Where did you move your GPTs and how was that process?

How to stop re-briefing Claude Code. Anthropic launched this only about a day ago. The problem this actually solves You know the forty minute briefing? You explain your offer. You upload your brand voice. You go back and forth on positioning until Claude finally gets it. And then you hit a fork in the road. You want two versions of the landing page. Or you want to keep working on the copy while something else builds the email sequence. Your old options were both bad. Start fresh and explain everything again. Or ask for both in the same chat and watch it get cluttered and slow. That is what these two commands fix: You type /fork and Claude Code makes a complete copy of your conversation. That copy becomes its own separate Claude, running in the background. Your original chat carries on exactly as it was. The copy remembers everything. Every message. Every file. Every decision you made together. It also keeps your settings, so you do not have to set anything up again.