Tylr

@zendadddy @EndorsiVal Frank, i agree, asha is amazingly talented and one of the nicest people to work with. We used to be on the same team at fb and mentored her in origami, sad to see her misjudged like this.

@EndorsiVal Asha is a super talented designer and was at Meta for 4y, full vest. Won the game!

You can’t make this shit up 😂🤦🏾‍♂️

anyone can cook. few are chefs. anyone can build. few are designers.

@TheCinesthetic Wilson Fisk

What’s a movie where the villain was way more interesting than the hero?

I can't tell if it's just me hearing the LLMs in people or if its just people adjusting their dialects to their peers (LLMs) but definitely been thinking the same

@kouhxp @steipete

WAT

@anamhira This has always been one of the biggest asks from designers at Meta. Of course, it doesn’t help when there are so many different possible experiences depending on the test you’re in. This definitely fills a void.

At Uber a big problem for design teams and engineering teams was design source of truth. No one knew what the app truly looked like, so weekly a bunch of designers would get into a meeting room and check that the engineers correctly implemented the figma designs that they made Now with coding agents throughput of changes has increased an order of magnitude and it has become impossible to manually keep up. Here we used the Revyl CLI to create a flow of every state in the Uber design, by navigating our mobile use agent on an cloud iOS simulator. This is something that would have taken a team of designers tens of hours to recreate manually; All done in less than an hour asynchronously with a simple prompt. Enable your team to know what your users are actually seeing and empower coding agents to give your users a delightful experience without any blindspots Get started with our new free trial and create a map for your own app 🗺️

This will be me with the quants momentarily

This is really neat but it’s not a design tool as much as it’s a design _production_ tool. The practice of design is mostly about what comes before production. There’s no doubt in my mind that all parts of software production will become automated very soon. Writing code, making web pages, putting pieces of a design system together etc. And that’s fine. I think few people actually enjoy this kind of production work. Wouldn’t it be better if we spent our precious time in life on what is more meaningful?! At the core, the practice of design is methodical; like architecture, not like art. In a nutshell: We find constraints, form comprehension of the whole and propose solutions that honor those constraints. First after that do we enter some form of production phase, usually prototypes first, learn about some constraints that were hidden before, loop back, prototype and then build the production-grade “final” artifact. These last few tasks are quickly losing value because AI tools can do it much faster (not yet better though) than humans. It’s simply just what has the best RoI for a business. Some companies and individuals will continue to spend human time on certain parts of the “production line” as a market differentiator, but it will cost them a relatively high price compared to competitors. Anyhow, I still haven’t seen a tool better than Figma that supports the actually-interesting part of the design process. I wouldn’t be surprised if Figma focused their products on that, maybe separating “products for production” of “products for ideation & exploration.” The latter would obviously still leverage AI, but not to do the work for me but rather to support my efforts the way a therapist helps me live a better life (not living my life for me.)

@PepperoniKVS @pardheevvv @claudeai Sure you can produce a bunch of junk at a higher rate than something of good design but that doesn’t mean it’s effective. Mass production of something doesn’t mean it’s better. Literally Mac vs PC logic

@tylr_r @pardheevvv @claudeai Unfortunately 99% of clients do not give af about “taste” lol

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

@PepperoniKVS @pardheevvv @claudeai If you’ve worked in the field of design you would know that people have always said this. Anyone could buy Photoshop when it came out and people said the same thing and yes there are a ton of ugly ps out there but that’s not replace real designers where it matters

@pardheevvv @claudeai This is entirely good for designers not replacing them lol. They have yet to ship the “Taste” feature lol

@claudeai Designers watching Claude take away their jobs

@nlaferle @bcherny Have you reconfigured your Claude.md prompt for 4.7?

@bcherny 4.7 is completely unusable for me. Completely ignores the specifics of my environment documented in detail in Claude.md, makes weird speculations, tells me it can't do things 4.6 has been doing forever. Massive backslide in usability.

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 🧵

@davidfelsmann @osttoo @steipete I agree, Gemini has been the best model since day 1 for everything except coding projects which i don’t use openclaw for anyways

@osttoo @steipete Runs also well with Gemini 3.1 Pro

They grow up so fast 🦞

@benhylak But have they been hacked? (What Mythos is really good at preventing/doing)

every engineer at anthropic has been using mythos for ~1.5 months. meanwhile, their uptime is horrendous, claude code still has rendering bugs, etc. one could conclude that it won't be the end of software engineering.

@Prof_Kalkyl @NASA These are slick!

Couldn't resist turning the incredible Artemis II photos from @NASA into a poster series

@jumperz @nathanclark_ I’m with Nathan on this. Sounds like you just asked an ai how to make it better and it told you this without anything to back it up

@nathanclark_ simply always ask your swarm to find the best settings that would work for you , never go with default, the prompt I dropped here is just good for any setup / scalable

if someone just updated openclaw and wants dreaming to actually work well, this is the simple guide from default to really useful. so, dreaming is openclaw's background memory system, It reviews recent memory + session activity, then promotes the important stuff into long-term memory.. think of it like: >short-term signals go in >useful patterns get scored >real memory gets kept >stale noise gets left behind 0- turn it on first /dreaming on check it with: /dreaming status then paste this prompt ===== open my openclaw config at ~/.openclaw/openclaw.json. and make these changes only: >under plugins.entries["memory-core"].config.dreaming, enable dreaming and set frequency to every 6 hours >under agents.defaults.memorySearch.query.hybrid.temporalDecay, enable temporal decay with a 30-day half life >under agents.defaults.memorySearch.experimental, enable session memory >under agents.defaults.memorySearch, set sources to memory and sessions >under agents.defaults.memorySearch.cache, enable embedding cache with 50000 max entries == that's enough to make dreaming way more useful than the default setup.. faster promotion, better memory quality, less stale context, and less wasted embedding cost the real value of dreaming isn't that it stores more context but it's that it decides what deserves to survive and you really need that. optional: btw this gets really strong when you combine it with BRAID.. so BRAID controls how the agent works and dreaming controls what the system keeps together you get agents that don't just act consistently, they actually compound useful behavior over time. i posted about BRAID before in here: x.com/jumperz/status…

@enjojoyy I thought it was odd the first time i heard someone say they got one for openclaw. Like, try anything else first. Granted Mac minis are nice regardless and are useful when used for anything else like a home server or something

Why is nobody saying that you don’t need a Mac mini to run OpenClaw? You can run it on a VM You can run it on a cloud You can run it on ANY computer You DON’T need to invest hundreds of $ just to try it out

@BlueBarronPhoto @Blissfullnotes @NASA From a photographer's eye, literally this. Just different editing going on

@Blissfullnotes @NASA Probably just editing? I upped contrast, added vibrance/saturation, and tweaked the white balance to get the photo on the right more similar to the one on the left. Different styles in post!

1972 ➡️2026 Apollo 17 ➡️ Artemis II

@rgbman1776 @gal_sion @GoogleLabs @stitchbygoogle i’d say it’s because templates are still made by humans rather than an AI which is using its entire training data in aggregate to create something that looks average of that. it still just outputs the most probable token so you would need a model designed for unique output

Yeah that's a fair comparison, but the difference to me is that I could throw together a site based off a template in about half an hour to an hour max. Despite it being a template (mass manufactured) it looks and works well, and is one of a million templates that could have been used. When I try vibe coding a site, it looks or at least always feels the same despite looking slightly different from one to the next. Also this is entirely based off of pure HTML sites with no CMS whatsoever. If I dared to use a CMS, at its current state it would be disastrous.

Introducing the new @stitchbygoogle, Google’s vibe design platform that transforms natural language into high-fidelity designs in one seamless flow. 🎨Create with a smarter design agent: Describe a new business concept or app vision and see it take shape on an AI-native canvas. ⚡️ Iterate quickly: Stitch screens together into interactive prototypes and manage your brand with a portable design system. 🎤 Collaborate with voice: Use hands-free voice interactions to update layouts and explore new variations in real-time. Try it now (Age 18+ only. Currently available in English and in countries where Gemini is supported.) → stitch.withgoogle.com