iiinova — where your digital self keeps evolving

Raduan Al-Shedivat @raduan.xyz · 18/11/2025

path to one person one billion dollar company 🙂 x.com/0xRaduan/st...

000

Raduan Al-Shedivat @raduan.xyz · 15/11/2025

doesn't get better than this:

000

Raduan Al-Shedivat @raduan.xyz · 13/11/2025

coding agents showed that everyone should use a monorepo.

000

Raduan Al-Shedivat @raduan.xyz · 26/08/2025

CC shocked that it was able to ship 3 weeks worth of work in 1 day:

010

Raduan Al-Shedivat @raduan.xyz · 25/08/2025

Interesting thing from "inference" newsletter: They write post methodology on how they wrote the post with LLM tools.

010

Raduan Al-Shedivat @raduan.xyz · 22/08/2025

Everything is just a system prompt + llm + tool calls + while loop.

000

Raduan Al-Shedivat @raduan.xyz · 21/08/2025

cooking something great obviously with claude code:

000

Raduan Al-Shedivat @raduan.xyz · 21/08/2025

Build Calm Confidence Software:

000

Raduan Al-Shedivat @raduan.xyz · 20/08/2025

claude code as a way to learn new english words:

000

Raduan Al-Shedivat @raduan.xyz · 20/08/2025

Talking to Claude about how premium software should feel:

000

Raduan Al-Shedivat @raduan.xyz · 19/08/2025

it's happening: I am migrating to uv. cc. @charliermarsh @astral_sh

000

Raduan Al-Shedivat @raduan.xyz · 19/08/2025

Loading screen. Onboarding almost ready.

000

Raduan Al-Shedivat @raduan.xyz · 18/08/2025

Windsurf team keeps shipping: If they continue at this pace, this will be a super interesting space to watch (and compete in). x.com/windsurf/st...

000

Raduan Al-Shedivat @raduan.xyz · 18/08/2025

farza on high quality launch videos / cluely:

000

Raduan Al-Shedivat @raduan.xyz · 17/08/2025

with every slop fake headline that perplexity pushes in their app, the less I will use it

000

Raduan Al-Shedivat @raduan.xyz · 17/08/2025

Using GPT-5 in @windsurf after wave 12, and it's noticeably better agent than what they had previously. Using high reasoning, it's slow, but instruction following is next level. Integration with DeepWiki also feels like an unfair advantage at this point. Very well done.

000

Raduan Al-Shedivat @raduan.xyz · 16/08/2025

If only people would think in decades: Then they would care more about proof of work... Than any cluely-level short term marketing stunt to get views on some post. Stop posting rage baits on this timeline and start building something great.

000

Raduan Al-Shedivat @raduan.xyz · 16/08/2025

We need grouping of tool calls back in Cursor. This is getting out of control quickly...

010

Raduan Al-Shedivat @raduan.xyz · 15/08/2025

From @zeddotdev blogpost by @conradirwin. My .02 cents: This will always be like that - humans in the drivers seat, but LLMs remove a ton of inefficency and help you translate inputs into outputs. Which means you will have flatter org structure and just faster pace of work.

000

Raduan Al-Shedivat @raduan.xyz · 15/08/2025

Gergely's keeps bashing Cognition, though their product keeps improving week over week, and many competitors copy what they've built into @DevinAI. Might be saying more about the audience of Gergely (devs from big tech, who haven't used Devin), than about the Devin itself.

010

Raduan Al-Shedivat @raduan.xyz · 14/08/2025

I want to use gpt5. But it's super disappointing around 50% of the time, and wastes my time. How do people use it successfully here?

010

Raduan Al-Shedivat @raduan.xyz · 14/08/2025

asking chatgpt to filter out SEO driven content

000

Raduan Al-Shedivat @raduan.xyz · 13/08/2025

Just can't imagine it getting better than this.

000

Raduan Al-Shedivat @raduan.xyz · 11/08/2025

Just realized there is a way to make Cursor Agent a main chat window. This should be the default view in a post IDE world. cc. @ryolu_

000

Raduan Al-Shedivat @raduan.xyz · 11/08/2025

everything is good about posthog, but it's super slow

000

Raduan Al-Shedivat @raduan.xyz · 10/08/2025

The more agency I give to an agent the more surprised I am with results.

000

Raduan Al-Shedivat @raduan.xyz · 10/08/2025

chatgpt reading vs code docs: "the page is long"

000

Raduan Al-Shedivat @raduan.xyz · 09/08/2025

Running these in parallel: - claude code - cursor - cursor-agent - windsurf - codex Any other to try? cc @devinai - I need a devin CLI.

110

Raduan Al-Shedivat @raduan.xyz · 09/08/2025

Built a message queue for ChatGPT like in @cursor_ai: x.com/0xRaduan/st...

000

Raduan Al-Shedivat @raduan.xyz · 09/08/2025

Which blogs I should read to learn more how people are using gpt 5?

010

Raduan Al-Shedivat @raduan.xyz · 08/08/2025

Early testing of gpt5: - amazing at following instructions - follows everything I told it in rules, similar to gpt4.1. - I let it debug issues on it's own - I still can't see using it instead of sonnet/opus for long-running high level use cases. - It's amazing in Cursor

000

Raduan Al-Shedivat @raduan.xyz · 08/08/2025

agentic coding pro tip: make all your devloop tools output token efficient

000

Raduan Al-Shedivat @raduan.xyz · 07/08/2025

all your sources, one home:

000

Raduan Al-Shedivat @raduan.xyz · 07/08/2025

not gonna lie, every time I see em-dash now questioning whether it's ai written or not not that it's a bad thing - I will still read the whole thing, if it's from good source. but would double-check it in case it's some hallucinated text. so not a bad side effect.

000

Raduan Al-Shedivat @raduan.xyz · 06/08/2025

Sidebar News. Inspired by @dubdotco / @steventey; built with the help of @21st_dev / @serafimcloud

000

Raduan Al-Shedivat @raduan.xyz · 06/08/2025

Found a new use-case: Vibe Reviewing. Been already using superwhisper / monologue by @every for a while. Now that I review more PRs than ever created by agents, realized that providing voice review is way better than me writing some things.

100

Raduan Al-Shedivat @raduan.xyz · 05/08/2025

Anthropic: - releasing 2% increase - realizes everyone is releasing something bigger - we are planning to release substantially larger improvements to our models in the coming weeks agents are accelerating x.com/AnthropicAI...

000

Raduan Al-Shedivat @raduan.xyz · 05/08/2025

figuring out how to make more delightful pictures for changelog:

000

Raduan Al-Shedivat @raduan.xyz · 05/08/2025

Great time to be building x.com/OpenRouterA...

000

Raduan Al-Shedivat @raduan.xyz · 05/08/2025

what if you had a separate inbox, but just for newsletters? > filter out emails by sender > read them / preview links that they sent > get AI summaries / key takeaways for each email > see stats and block useless senders in one click shipped and available at summate[.]io

000

Raduan Al-Shedivat @raduan.xyz · 05/08/2025

ask ai to write design docs, once it understands your code

010

Raduan Al-Shedivat @raduan.xyz · 05/08/2025

Very interesting: since chatgpt launch, data centers spending only increasing and office construction is only decreasing ignore this data at your own risk.

000

Raduan Al-Shedivat @raduan.xyz · 04/08/2025

Good take from @balajis. Doubling down on your prompt and building better systems for verification is what you need to be spending your time on. Improving inputs. Verifying outputs.

020

Raduan Al-Shedivat @raduan.xyz · 04/08/2025

ai is everywhere. you don't need to read 99% of what's on the internet:

000