Duke of Saxony

@markoilico Yay, pls.

If you're now designing or redesigning a website, this will help you a lot. I recently curated the best hero sections, footers, social proof and other website parts because I got tired of having 15+ tabs open (even with Mobbin). Giving it away 100% free. Comment on this post, and I'll send a Figma link to your inbox!

@poetengineer__ i can't suscribe :(

i built a dashboard for my claude code sessions: 254 sessions across 58 projects over 3 months 🤖🧚‍♀️ - 3d terrain map of token usage over time - session cards with first/last prompts, hover to expand - click to resume any past session in-browser - activity heatmaps, project treemaps code available for my x subscribers <3

@joseflorido @lucas__crespo @gravicle @LumaLabsAI Great for parallax’s.

@lucas__crespo @gravicle @LumaLabsAI I don’t think layers add value. They were needed in the past. With current editing models you just annotate or prompt your desired changes and regenerate the image

okay it seems like @LumaLabsAI new uni-1 model is actually on a category of its own You can give it one complex composition and its able to extract each layer as a new image generation Are there any other models that can do this?

@theo Try this: github.com/gsd-build/get-…

Just let Opus go for over an hour on a new feature. When it was done, I asked how I can test it. 20 minutes later, it realized I can't test it because it did the whole thing entirely wrong. Idk how you guys use this model every day for real work 🙃

@AlfieJCarter CLAUDE

If you don't have my "Claude Power User Playbook" yet... The one I built to get 10x more output from Claude every session with a complete system across settings, prompting frameworks, file creation, memory management, and advanced workflows... Just comment "CLAUDE" and I'll DM it to you for free (must follow)

@crypto_nite975 @aiedge_ Twenty years of experience turns out to be the moat.

@aiedge_ The people getting the most out of AI right now aren't the engineers. They're the ones who know their field so well they can tell the tool exactly what to do. Twenty years of experience turns out to be the moat. Somewhat inconveniently for the pivot-to-tech crowd. #AI #expertise

@slopppcorp @theo care to share?

@theo I'm going to download the transcript from this and give it to codex to have it audit my own setup

You should delete your CLAUDE․md/AGENTS․md file. I have a study to prove it.

@pcts4you @openclaw @MistralAI @grok Plugin compatible with other browsers?

@openclaw @MistralAI @grok tell me more about the OpenClaw bruwser plug-in mentioned here

OpenClaw 2026.2.22 🦞 🥐 @MistralAI (chat + mem + voice) 🌍 Multilingual memory (ES/PT/JP/KO/AR) 🔄 Built-in auto-updater (off by default) 🔧 Cron: parallel runs 🛡️ 40+ security hardening fixes And a browser extension that actually stays connected. github.com/openclaw/openc…

@Legendaryy Liked, Bookmarked, Followed, Thank Youd!

Used 1.4 billion codex tokens this week working with OpenClaw. Here are the 10 most important things I learned. Give this to your agent. But most importantly have fun learning, tinkering and enjoy the journey.

@floriandarroman Lab

Ok, this blew up! I’ve got hundreds of questions in my DMs after this post. So I launched an OpenClaw Community for founders. Where you can get my full 11-agent setup, weekly lives, AMAs, and a community of founders like you! Comment “Lab” to get the link.

@higgsfield_ai Sweet.

@dztrucktion @DefiantLs She’s talking about the “majority of us” which means “us-liberals“

@DefiantLs Obviously the “majority” doesn’t hate him.

Liberal woman: “We are watching the downfall of Trump and his power”

@thedorbrothers @realDonaldTrump @elonmusk @ElonMuskAOC @ElonMuskPD @Asmongold @h3h3productions @DramaAlert @AngryTomtweets @codewithimanshu @samtripoli @sama @libsoftiktok @Rainmaker1973 @AutismCapital @bennyjohnson @TiffanyFong @TheFigen_ @ianmiles @venturetwins @joerogan @andrewschulz Slick Slop.

Pop-Tards Vol. 1 Song: Denzel Curry - HOT ONE ft. TiaCorine & FERG @realDonaldTrump @elonmusk @ElonMuskAOC @ElonMuskPD @Asmongold @h3h3productions @DramaAlert @ai_for_success @AngryTomtweets @codewithimanshu @samtripoli @sama @libsoftiktok

@StevieMac03 @Kling_ai Cool idea and it looks great but the physics, way off, a mammoth wouldn't be able to jump around like a puppy, it's just too heavy.

War Mammoth 🦣 quick @Kling_ai 2.6 generation. 🔊🔊

@SGabardi1111 @elonmusk @grok The pearls look terrible...

@elonmusk @grok She wears pain like pearls

Made with @Grok Imagine Download the latest version of the app. apps.apple.com/app/id66703248…

@SriramMadras @elonmusk @grok Sure looks realistic for sure just not like Grace Kelly.

@elonmusk @grok I asked @grok to imagine Grace Kelly in front of Taj Mahal, and this is so realistic.

@kobyof @MichaelTopo @mark_k Many models let you train a Lora for stylers, characters, objects etc

I see what you're saying, but I'll argue that MJ is more taste oriented, product-wise. Take this new feature for example. It's very specific for people that want and need to refine their photos according to specific styles. It's not impossible with other models, but product-wise that's not their direction. So my bottom line is that while MJ will fall behind model-wise, they might be able to differentiate with the actual product. x.com/midjourney/sta…

Is it over for Midjourney now, or can they still grow? I think diffusion models are hitting a wall, they can't reach the intelligence of a large multimodal model. So yeah, I think it's over for MJ, at least in the longer term. What do you think?

@javilopen Left

You can only chose one and the future of a super important Magnific spell depends on this. Left or Right?

@sciencegirl That will save us a Forrest of toilet paper.🧻

Japanese researchers have developed a soft robotic tongue that mimics the sensation of a real tongue it has potential applications in therapy, elderly care, and robotic pets.