Long post incoming, but I'm desperate at this point and need the internet's help. (For the TLDR, check the replies for links and action items)
So my little sister Chizo has been fighting leukemia for the past 2.5 years. She's been in remission twice, once after a bone marrow transplant from our brother and then again after a CAR-T treatment after another relapse last year. She is now in her third bout of the fight, as the leukemia has returned yet again in December of last year.
She's spent the majority of this year in the hospital and they tried an alternative CAR-T treatment, which did not work this time. Afterwards, the doctors gave her two options: manage her pain and spend time with her family and loved ones until it's time to pass on, or to take a In order to address this third bout, they tried an alternative CAR-T treatment that did not work this time. The doctors gave her two options:
1) Manage her pain and spend the rest of her time here with her family and loved ones
2) Take a life-threatening chemotherapy treatment that can lead to heart/liver failure based on the intensity of it to bridge her to her next treatment, whether it's another CAR-T treatment or a bone marrow transplant if they find a donor.
She's a fighter, so she chose the chemotherapy treatment and is still fighting to this day. So I'm here to ask for y'alls help as she continues this fight.
Digging into reports, most of the fastest burn came down to a few token-heavy patterns. Some tips:
• Sonnet 4.6 is the better default on Pro. Opus burns roughly twice as fast. Switch at session start.
• Lower the effort level or turn off extended thinking when you don't need deep reasoning. Switch at session start.
• Start fresh instead of resuming large sessions that have been idle ~1h
• Cap your context window, long sessions cost more CLAUDE_CODE_AUTO_COMPACT_WINDOW=200000
We're rolling out more efficiency improvements, make sure you're on the latest version.
If a small session is still eating a huge chunk of your limit in a way that seems unreasonable, run /feedback and we'll investigate
Pro tip: Use Oracle (GPT-5.2) in @AmpCode free to review your Claude plans and code. $10/day of free credits. Usually catches things Claude missed.
Been paying $20/mo for Codex just for this use case, and I still need to monitor my usage.
I'm in Sydney this week with @RealGeneKim, getting ready to conduct a week of Vibe Coding workshops, compliments of Commonwealth Bank of Australia, our generous sponsors for this trip.
I realized this morning chatting with Gene that we've identified a bunch of new and very useful tips about agentic coding, particularly with swarming, which weren't in our Vibe Coding book. I took half a dozen of them, and wrote them up in a new post.
Here's the list; read the post if you'd like more details.
1. Software is now throwaway — expect < 1 year shelf life
2. Agent UX matters at least as much as Human UX
3. Spend 40% of your time on code health, or else you’ll wind up spending >60%
4. You might be too early: Some AI projects are ahead of their time
5. The Rule of Five: When in doubt, have the agent review its own work 5 times
6. Swarm where you can, but beware the Merge Wall
Enjoy! https://t.co/KiaDLqZ1Bv
Built a demo for @Shopify@base onchain summer. It stores affiliate referrals onchain and automates payouts for purchases.
With smartwallet, customers receive discounts at checkout without entering promo codes.
Thoughts?
https://t.co/NHivfC0FrG
@Alex_Danco@ShopifyDevs
Hey @RebuyEngine, is there a way to reduce the CSS bundle size?
Your app is shipping 196kb of CSS and it's affecting our store speed.
Are you including the whole Font Awesome library in there?