Pinned Tweet
In my time coding with AI, I realized quickly that, no matter how large the context window, agents forget project details constantly. So, I came up with a process to solve that. And it worked. Now I've bundled it up into one handy tool for everyone. clauderizer.com
I wrote this song's lyrics and the original version in 2012 in response to Occupy Wall Street. I had AI remake the song in 2024. Then I made a music video for it. With Opus 5.5 and Suno 6 out now, I threw the old content at it for a glow-up. I present to you, High Command.
Collin Cusce 🔺⚔️ retweeted
The Avalanche Audit Marketplace is live on the Builder Hub 🔺
One request reaches all Ava Labs vetted firms. Quotes stay private, you pick one, and the program can cover up to 75% of the cost.
$0 fees for builders and auditors.
Request quotes 👇
Collin Cusce 🔺⚔️ retweeted
Just when you want to give Zuck some praise
In a completely unsurprising turn of events, Meta's Muse AI is stealing Apple Messages, past and present, and uploading the contents to its cloud, even if explicitly told not to. By @Amber_M_Neely
appleinsider.com/articles/26…
Collin Cusce 🔺⚔️ retweeted
If vibe coding keeps evolving at this pace, what happens to software developers?
Agent code quality may look worse to a human observer, but in my experience agent build quality is better.
Features have less bugs on launch and tend to "just work", whereas human-driven builds always tended to be myopic and fail for embarrassing reasons.
Collin Cusce 🔺⚔️ retweeted
The tutorials in Elowyn grants you 100 EWA each, play five and that's a card pack I didn't have to buy
then the part I really like is that most card games decide what an upgrade does for you but here you pick either cheaper, tankier or harder hitting, and every option costs you something
top tier is eternal. five copies of a card go into one.
@Earthwisegames @Immutable
Collin Cusce 🔺⚔️ retweeted
Hi,
Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan.
Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago.
(a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want.
(b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions.
(c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent.
(d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet.
I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news.
Codexingly,
Tibo
Collin Cusce 🔺⚔️ retweeted
A timely reminder: you do not hate Aella enough.
Collin Cusce 🔺⚔️ retweeted
Replying to @DanFessler
You know the tech is legit because it keeps converting all of the haters










































