iiinova — where your digital self keeps evolving

If a CVE still needs a human to open the PR, you don't have a factory.

101

there's nothing more satisfying than shipping a database optimization Gives more dopamine than hearing ATM chrrrrr

000

I’m still finding Fable a better choice for SWE. Astra is no doubt a great upgrade, but I think it shines more in other use cases like creativity and investment research

000

Yousuf K. @yousufkalim.com · 01/09/2026

Chat has won. It's all chat + computer from this point on

000

Claude is watermarking text now. Fable 5.1 and every model released after Aug 2 gets an imperceptible watermark on text outputs. everyone, not just EU users.

000

Yousuf K. @yousufkalim.com · 28/08/2026

Cursor can now go from a blank prompt to a repo, live preview, and Vercel deployment This removes so much dumb setup for small apps, you can figure out if the idea is even worth keeping before touching repo/deploy stuff

Yousuf K. @yousufkalim.com · 28/08/2026

Perf + better defaults for humans and agents is the kind of win most teams only talk about.

Yousuf K. @yousufkalim.com · 26/08/2026

Somewhere along the way we started benchmarking the setup instead of the actual work

Yousuf K. @yousufkalim.com · 24/08/2026

These tools can be incredibly powerful for localized, well-defined tasks. When you combine them with systems that can generate those tasks from telemetry, you get a self-improving system.

000

Yousuf K. @yousufkalim.com · 22/08/2026

Insane for one release 🤣 I mean they rewrote the whole runtime in rust 😂 crazy things happening around the world!

Yousuf K. @yousufkalim.com · 21/08/2026

Rofl that both OpenAI and Asana management believed that it would take FIVE years to migrate Enzyme to React Testing Library. What amusing BS! I imagine it went like this: Manager: “How long will it take? Give me SOMETHING” Dev (annoyed): “FIVE YEARS OK?? Now leave me alone.”

030

Yousuf K. @yousufkalim.com · 20/08/2026

Opus 4.7 was where I started feeling it too. Not necessarily dumber, just way more constrained and weirdly less enjoyable to work with

Yousuf K. @yousufkalim.com · 20/08/2026

Grep hygiene is such a good term for this. You can give an agent the whole repo and it’ll still find five abandoned plans before the file that actually matters.

100

Yousuf K. @yousufkalim.com · 17/08/2026

I don’t think people realize how much Claude’s personality was the product You can improve benchmarks all day, but if every convo starts feeling defensive and suspicious and overly sanitized, congrats you’ve killed the exact thing that made people want to use it.

000

Yousuf K. @yousufkalim.com · 12/08/2026

Grok 4.6 just ranked #1 among AI models tested under a $5 workload budget Grok's intelligence per dollar is getting ridiculously high There are almost no other frontier models delivering this level of intelligence at this price

Yousuf K. @yousufkalim.com · 08/08/2026

We spent years securing against humans. Now we need to secure against relentless attacks at machine speed 🌚

133

Yousuf K. @yousufkalim.com · 07/08/2026

I’m pro AI and I read a lot, but I won’t read a chapter of a book written entirely by AI. The author’s experience, emotion and effort are part of the book.

Yousuf K. @yousufkalim.com · 06/08/2026

If a usage reset is close and there’s plenty left, fast mode makes perfect sense. Finish the feature now without burning the next window.