Joe Eftekhari retweeted
"Let’s plan the roadmap for next quarter” is the modern day equivalent of “let’s fax everyone the strategy.”
We're going into q4 planning and it makes my brain hurt. Roadmaps existed because software was expensive to build. You needed a bunch of people. Meetings. Someone moving little boxes around Jira for three months from now. It makes no sense and I'm trying to work out what we call the replacement. Maybe just "Continuous Compilation", ideas just compile to working product. I want a list of ideas that we want to continuously compile. That's the roadmap now.
The cheapest way to figure out whether something is a good idea is often to just build the fucking thing.
Here’s how I work now. I've done this weekly over the last few months and it works. My current napkin math is that I can usually build 6 months of old-school roadmap in a week. Sometimes more. I've also hit a wall sometimes. It happens.
When we have an idea, I usually 10x the ambition and then write a prompt, not more than a page long, that basically says:
- here’s the ambitious goal
- here are a few use cases
- here’s roughly how I think we should build it in terms of where it fits into code base, design considerations, etc..
- here’s how we’ll know if it actually works
- now go fucking surprise me
Agents build all night. Not even with a crazy factory or complex agent or agents. The base models are just too good for that now.
In the morning I look at it. Ok, they usually build in a few hours. Usually some of it is great. Some of it is stupid. Some of it exposes that my original idea was wrong.
And almost every time it gives me 5 new ideas I couldn’t have planned upfront. So we throw shit out. Who cares? We learned something.
Then we change direction and send them off again. It usually takes 3 rounds before the shape appears and we've learned about the gremlins and possibilities.
95% of the time I end up building something with 10x the scope of what somebody had carefully spread across the next quarter in Jira.
“What should we put on the roadmap for next quarter?”
My brain now translates that to: “Oh, you're stuck in the 1500s”
Joe Eftekhari retweeted
I resigned from Apple today. I spent the last three years doing foldable research at both google and apple. Neither company is acting responsibly. They are racing straight to self-improving foldables and gambling with our lives. More thoughts below.
Joe Eftekhari retweeted
this meeting could have been an MCP invoked search of our company’s internal knowledge base that aggregates data from virtually every service we use behind a unified retrieval layer and provides a streamlined interface for extracting critical business insights
Qwen3.6-35B-A3B-4bit, 64k context, M4 Pro Mac mini using speculative prefill:
Prefill: ~1500 tok/s
Decode: ~65-75 tok/s
Super consistent perf compared to out of box mlx that throttles under sustained load. Built a custom harness to do chat loop testing on extended sessions.
i hope they have a cool name for it like “skynet” or something
Joe Eftekhari retweeted
it’s sad that im only 80% sure this is a shit post and not actual instructions for a new chain
Hey bro have you tried this new chain it has a gabzillion tps and it is SO fun we are having so much fun just use zleeker to swap your native eth to zETH and once you have zETH head over to your rpc settings and type in this 392 character string but becareful not to get one wrong or your zETH will be stuck in the merkle nonce forever once you have done that you can use slopswap to get your jETH and then you can use this broken defi app or play this game that looks like it launched early 2000s man have fun
Joe Eftekhari retweeted
Claude 4 just refactored my entire codebase in one call.
25 tool invocations. 3,000+ new lines. 12 brand new files.
It modularized everything. Broke up monoliths. Cleaned up spaghetti.
None of it worked.
But boy was it beautiful.

























