yo @ThePrimeagen, any plans in the works to bring terminal.shop coffee to the uk?
Absolutely smashed this one @iamakulov, bravo!!
We spent a year working with the Lighthouse team on how it simulates slow phones. Lighthouse 13.6 fixes two flaws that made fast Framer sites look slow in PageSpeed Insights. Your site was already fast. Now your score shows it. Full write-up: framer.com/blog/lighthouse-1…
been playing Pokemon Platinum Together with the wife over the last week and it's so much fun, we're doing a soul-locke randomizer
If you've always wanted to play gen4 with friends super recommend it, here's the current team.. only two losses (both to crits!) so far... 😬
cal morris retweeted
Introducing Agent Templates, Marketplace templates built to work with the Framer agent. Each one ships with skills, a design system page, and a short video that shows how the pieces fit together. Read the full update and guide framer.com/updates/community…
We just shipped a small update to our @Framer Community Analytics which now updates the remix count for templates as soon as they occur, check it out! framer.com/community/analyti…
How else can we make the entire of Framer better? 👀
cal morris retweeted
I can’t help but weep:
lighthouse (starting with v13.6) no longer punishes single-page apps for loading a lot of JS ahead of time. wild times! some Framer sites (previously incorrectly scored) get +20-30 perf points.
we’ve just had spooky season, now it’s time for the most magical time of year; what would you change?!
cal morris retweeted
Compared to External Agents, Framer MCP is about twice as fast and follows instructions better, because it runs on the same tools as our in-app agent. Setup is simpler too: one approval with your Framer account instead of an API key plus a sign-off for every project, and no CLI or skills to install and keep updated. It also isn't limited to coding agents in the terminal. It works in ChatGPT, Claude, Cursor and any other client that supports MCP, on desktop, web or mobile.
cal morris retweeted
Tip for faster Oxlint on CI: Turn off "warn" rules.
No one reads warnings on CI, so this is a no-brainer. ESLint v10 does this by default, oxlint currently doesn't.
Effect on Framer's monorepo: 100s → 66s, 51% faster.
cal morris retweeted
Get 50,000 agent credits for every client site you plan to switch to Framer. The new Switch program helps you move clients faster and easier, without spending on credits.
Switched? 50% of what we make on your client’s first-year subscription is yours too. framer.link/switch
cal morris retweeted
Skills just shipped @framer so I've turned one of my favourite engineering principles into a reusable skill:
/𝚘𝚗𝚎-𝚝𝚑𝚒𝚗𝚐
It reviews your site, finds a useful improvement and makes the change.
One focused improvement at a time, ready for you to review.
now we need the world first NaN Inf via decision model to make jimbo proud
As promised, here's @Cloudflare's new model "Clef" using NVFP4 quant playing @BalatroGame and winning at ante 8, fully offline on a single RTX 5090!
The last play is mindblowing, very nice combo!
I'm very impressed that it managed to beat the game. Balatro is not a simple game and this model doesn't have a CoT to plan things better like LLMs do. It's not a god-like model, it still makes some decisions that aren't very good but it managed to beat the game in the end, so ¯\_(ツ)_/¯
The response time is not fast, almost 4s on average. The larger the context size the slower it gets. Total playthrough duration was 19m 40s (~3min faster than GLM 5.3 Flash NVFP4 in the sparks).
I had to get close to the 16K token limit trying to squeeze as much info as I could while also attaching a lower resolution screenshot of the game (640x426) thanks to the vision encoder in the model 🙌
This one was especially tricky, as I had to make the options clear and try not to bias and make it an agreeable machine by adding options that I would consider "bad". I can't say that it decided well if there were no bad options to choose from.
The economy seems very different from the GLM 5.3 Flash playthrough, I might give GLM another run with the latest state of the harness to see if it will also spend more money instead of just keeping it.
Also it used a lot of discards, which was quite interesting.
I still think there are a few issues with the harness and I will keep improving it as I try more models.
@CloudflareDev
