thinking of making Edge-oriented starter kit based on Cloudflare 🔥
→ @Cloudflare (Workers, D1, R2, KV, CDN)
→ @tan_stack (Start, Router, Query, Form)
→ @better_auth
→ @polar_sh
should I?
ps. making it open-source 👀
Tutorial: How to get more installs by translating your Shopify App Listing
Many Shopify App founders are looking to get more installs but forget about this method:
Translating your app and listing into different languages is very powerful.
Back in the day, 2% of my users were Italian. I translated my listing, and it jumped to 7% in a month.
The idea is simple: If people from a country use your app, more may need it.
So push them in this direction by translating everything.
How to find the languages you have to translate your listing into:
1. Connect your Shopify App to App Store Pulse
2. Check in "Listing Analytics" which countries are visiting your app
3. Translate your app into these languages.
Important: Keep the main keywords untranslated (such as "bundles") and add the translated ones as well (for example, "offres" in French)
A non-VPS alternative:
Setup ollama with a $20/mo cloud plan. When Claude or Codex models are having problem, just start "ollama launch codex -- --yolo" or "ollama launch claude -- --dangerously-skip-permissions" and then select glm-5.2, kimi k2.7 code, or minimax m3.
This is normal part of my workflow to minimize interruptions.
You could also figure out an alias "gclaude" to startup claude code with gpt-5.5 codex models. I would do this because of AI harness with my preferred coding agents.
A WEB STUDIO CHARGES $35,000 FOR AN ANIMATED SITE. THE SAME BUILD NOW COSTS $12 - CLAUDE CODE WRITES, HIGGSFIELD RENDERS.
Every agency billing $100-149/hr is just three departments.
Here's each one, collapsed into a single agentic session.
SYSTEM 1 - THE MOTION STUDIO (Higgsfield)
Cinematic clips pulled from 30+ generative models - hero shots, transitions, ambient loops.
→ This used to be a motion artist on retainer. Now it's a prompt.
SYSTEM 2 - THE DEV TEAM (Claude Code)
Scaffolds the site, writes the GSAP ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset.
→ A full scroll-driven build with zero hand-coded keyframes.
SYSTEM 3 - THE DESIGN DEPT (baked-in cinematic layer)
Six effects with no config: film grain, particles, vignette, glass cards, color tints, scroll pacing.
→ The polish that justified the invoice - now it ships by default.
Three departments. One operator. One pass.
What used to take a designer, a motion artist, and a developer through weeks of handoffs now runs in a single session - for a Claude subscription and a few dollars of Higgsfield credits.
The studio was never the talent.
It was the overhead.
And the overhead just became three systems.
Reply "web-site" to this post and I will send you the step-by-step Playbook 👇
I made a dynamic chart to illustrate Bitcoin's 4-year cycles
It keeps updating forever adding new cycles along the way
The next cycle starts on October 31, 2026 so theoretically that should be the bottom
https://t.co/YK5vR7JUYJ
NVIDIA just made AI detect objects 10x faster by deleting one step.
It's called LocateAnything, and it removes the biggest bottleneck no one else was fixing in vision-language models.
Normally a model builds each bounding box one coordinate token at a time. 100 objects means thousands of tokens before an answer. NVIDIA scrapped that: their Parallel Box Decoding predicts the whole box in a single forward pass, as one atomic unit.
→ 12.7 boxes/sec on one H100
→ 10x faster than Qwen3-VL
→ +3.8% F1 on LVIS, accuracy up, not down
→ 3B params, runs on one consumer GPU
Treating the box as one unit keeps its coordinates tied together, which is why accuracy climbed instead of falling.
One model handles detection, GUI grounding, OCR, and document understanding, ready for computer-use agents, robotics, and document pipelines.
100% open source, weights, code, demo, and paper all live.
google is casually giving developers 1M tokens per minute for free 😳
no credit card
no subscription
just official access through google ai studio
what you get for $0:
- 1M TPM on gemini 2.5 flash and pro
- deep reasoning with pro + ultra-fast inference with flash
- native text, image, audio, and video support
- instant api key generation in seconds
why this is huge:
> no fighting strict free-tier limits
> no topping up credits just to experiment
> no paying middlemen for api access
getting started takes less than a minute:
1. go to https://t.co/9vHiKEo4K2
2. sign in with your google account
3. choose flash or pro in the playground
4. generate an api key and start building
pro tip:
use flash for high-volume workloads and save pro for tasks that need stronger reasoning to get the most out of the free limits
the best part?
you can access all of this without spending a single dollar
free tiers can change anytime, so enjoy it while it lasts
bookmark this and grab your api key before everyone else does 👀
This is why native menus feel so much better.
Prediction cone / safe triangle — the invisible area that stops submenus from closing when you move diagonally.
props @sorenblank