Sidd

@PrajwalTomar_ @ignytstudio Council via Paper Clip or just a custom local setup with Openclaw/Hermes?

One AI model will lie to you. Three won't. Before any BIG business decision, I run a "Model Council." GPT. Claude. Gemini. Same question. At the same time. Inside Perplexity. This month when I was evaluating a new app category for @ignytstudio. → GPT said the market was underserved and growing fast → Claude broke down competitors and found a speed differentiation angle → Gemini flagged a regulatory risk NOBODY had mentioned That regulatory flag would have cost me months of rework post-launch. No human advisor caught it. Three AI models running simultaneously did. My decision framework: → All three agree? Move fast. → Two agree, one doesn't? Dig into why. → All three disagree? Do more research. The council doesn't replace my judgment. It stress-tests it.

Oh boy!

@dannyvankooten Freshdesk

What's everyone using for providing email support, if not HelpScout?

@chrislema @mikemcalister @bymilesai @BuildWithOllie Thanks Chris! Value as always. I am going to try both.

Good news - @bymilesai & @BuildWithOllie are both doing incredible things with AI and design for WordPress! chrislema.com/ai-can-design-…

@webjuice_ie I don’t think that time has come yet.

After 15 years working with WordPress, we finally moved our own agency website away from it. Old setup: WordPress + Elementor + plugins New setup: Astro + Tailwind CSS + clean static architecture The difference is massive: - faster loading - cleaner code - less maintenance - better Core Web Vitals - no plugin bloat - no Elementor drag - AI controlled This is the standard now. If your business website feels slow, bloated, or impossible to improve, it probably doesn’t need another plugin. It needs a rebuild.

@Teknium Thank you! :)

@abpcontent I'm here to help if you need any, docs are great place to start; hermes-agent.nousresearch.com/docs

There's so much to explore in Hermes, check out the guide:

@andrewhoyer Serious discussion with the owner. Followed by choose your poison. Drink the poison and off you go!

Choose your own adventure: You open up a new WordPress client's site and see this. What's your next move?

Yes!

@lifeof_jer Well done Railyway! Backup redundancy has saved us more times than I can count! I am just glad man that you have it down to just 46 min of lost data vs 0. Praying things absolutely normalize in this coming week!

It's incredible. 46 minutes of lost data is a no-brainer compared to where we were at before. Props to Railway for pulling that off. We should also require human intervention for deleting volumes in production. We need to work with him to either: use proper backups that are not on the same volume, or rename backups to snapshots.

This scares me as we get more embedded into AI systems.

@natmiletic @DessignCo 100%. We have those clients too!

@DessignCo Some of our clients still want to hit 90% on mobile We always tell them that it doesn’t matter but we will oblige

Does site speed actually move the needle on rankings, or are we all just obsessed with green PageSpeed scores that don't convert?

If Claude breaks because of the too large an image upload use /rewind

@stevejonesdev @famousish @photomatt Miss it!

@famousish @photomatt You know we used to make websites that looked like this. We’ve lost something along the way. 🤔

@photomatt told me to check out the new GPT Image 2 Model and boy do I love it. I'd do anything for WP.org to have this vibe.

@jstamby @AlexFinn Big miss. 24/7 is a big deal. Run the $200/month 24/7 and see how fa you get. Not to forget everything remains private!

@AlexFinn Bro, we’re all chillin. You spent $20k while we’ve paid $200/month for frontier models over the last few months. At this rate we’ll be able to run quantized models on less than half the ram and hardware requirements by the end of the year so half of what you’ve spent.

It happened. An open weights model just dropped that benchmarks higher than Opus 4.6 is out If you have 2 Mac Studios w/ 512gb, you can run Opus 4.6 level intelligence completely for free on your desk I warned you this would happen months ago. Now Mac Studios and Mac Minis are sold out The next Mac Studio has been delayed until Q3/Q4. The price will be significantly higher I told you this was going to happen. Intelligence explosion. Hardware bottleneck. Increased efficiency Luckily I picked up 2 Mac Studio 512gbs, 2 Mac Minis, and a DGX Spark I will be loading this up in the next couple of days and will have completely private super intelligence running for me 24/7 I’m telling you right now by end of year we will have a local version of Mythos. It’s 100% guaranteed You called me crazy but every single prediction I’ve made has turned out to be true These models will only get more efficient and require less hardware. But that hardware is only going to get more expensive Local/open source is so obviously the future and if you’re still denying this now you are delusional

🥹♥️

@anomsiiwa Exploiting ‘child safety’ allows them to trigger people’s ancient instincts and bypass critical thinking. It’s the ultimate backdoor to manipulate the masses through fear and anger.

To check if your Google Workspace has been compromised by the same tool that compromised Vercel: 1. Go to admin.google.com/ac/owl/list?ta… - This is Google Admin Console > Security > Access and Data Control > API Controls > Manage app access > Accessed Apps 2. Filter by ID = …v79i7bbvqj.apps.googleusercontent.com - This is the ID of the compromised OAuth app If you see an app after filtering, you have potentially been compromised

Superwhisper's next update might be too powerful to release publicly. The new voice model is so fast at transcription it started finishing sentences users hadn't thought of yet... We even put it in a sandbox and it dictated its way out. It also identified a flaw in the English language that had gone unnoticed for 600 years. Linguists have been informed. Out of an abundance of caution, we are withholding the update until further notice. Sincerely, The Superwhisper Team