Is this bad boy faster? Yes.
Will it have some bugs? Yes.
Do we want to hear about them? Hell yes.
When you find something that’s off, hit the “Send Feedback” button in the Launcher so we can tackle on the road to release.
More deets on how to get started in the blog:
2026 indiehacker playbook:
> complain on X about how [entrenched SaaS product] is so expensive now
> people like and agree
> idea validated!
> build 83% cheaper competitor
To be fair, this is a pretty decent playbook.
@Petrik_Dev Indeed. I've seen it a few times in my career. The move from asm to C, the move from C to C++, the move from bespoke to commercial engines... and now agents. At every inflection point there are people who peel off and do something else.
@Petrik_Dev Indeed. I've seen it a few times in my career. The move from asm to C, the move from C to C++, the move from bespoke to commercial engines... and now agents. At every inflection point there are people who peel off and do something else.
I have noticed some addiction patterns with AI that I saw with drug use 20 years ago. With myself as well as other people. Obviously on a much smaller and less damaging scale. Things like the rush, impulse, rationalization, etc. More in my latest video:
youtu.be/_OT4RKiHNW8?si…
This reminds me of a time around 2020, when new front end tool, library or framework was released or updated almost every month, and I had kind of anxiety about how much there are to learn. And then a client comes with a website from mid 2000 without even jquery 😄
My observation going back to my old university was the same: most students had no idea what Opus 5.5 is (a week after it was out), don't follow tech news, have never used Codex or Claude Code or Cursor... the university now is negotiating a Kiro license to show them something
It
@GergelyOrosz The thing about the "bubble" is not only information but adoption as well, not every company is or will be using this tools, however unbelievable this could sound.
My observation going back to my old university was the same: most students had no idea what Opus 5.5 is (a week after it was out), don't follow tech news, have never used Codex or Claude Code or Cursor... the university now is negotiating a Kiro license to show them something
It was pretty surpsing to me how different of a "bubble" I am. Just a very different inforamtion bubble there, it felt
Sometimes it feels like the product strategy for many of these coding agents is "YOLO"
On one hand, this makes sense because the industry + capabilities keep changing
On the other, weird to learn about these things from random social media posts. So much change, week-over-week
🚨Anthropic removes Cowork's local option for Pro/Max tomorrow.
New tasks run in the cloud. Existing local tasks stay on your computer.
Anthropic says your sessions and files "live with your Claude account and go where you go."
Where is my data, and who can access it?
Side note. The idea that current models are conscious is absurd and downright offensive. Do not confuse competent information processing and sentience, they are wholly unrelated.
You can be entirely incompetent at everything yet fully conscious, like a toddler, or extraordinarily competent in one or more domains with absolutely zero consciousness, like a calculator, a chess engine, a self-driving car, or an AI chatbot.
Possessing the "circuits" for competent information processing in a given domain, whether through training or hardcoding, does not produce qualia, subjective experience, emotions, or suffering. Calculators do not "feel" arithmetic and they don't get tired or annoyed when you give them larger numbers to process. To argue otherwise is ontologically absurd. Current AI models are effectively calculators scaled to a very large number of competence circuits across many domains, etched via gradient descent.
Last open lesson of the year! How to crack the AI Evals Interview!
AI Evals are now a part of an increasing number of AI job postings, and you're now more likely to encounter them in interviews.
I've helped design quite a few evals interviews, so I know what kinds of traps exist, along with nuanced things companies tend to look for. I'll discuss this, as well as how to structure a take home or report to help you think through the problem clearly.
Tuesday Oct 6, 8:30am PT. This one assumes some basic evals knowledge. Read this first if you're new to the topic to get the most out of the session: hamel.dev/evals-faq
Sign up here: maven.com/p/07e7c7
If you're starting a SaaS aimed at devs today, I think a good filter is "how fun is this to build?".
If it sounds like a fun challenge, you're going to get replaced on a lunch break.
If it sounds like a total nightmare to build, then you might have a stronger moat.
this is exactly what happened with Mintlify for us.
I had 25% of my Claude max leftover on Friday night, I got an email from them saying they were increasing prices, so I replaced it in ~12 hours with about 25 minutes of actual effort.
The argument was always “no way will they waste time vibing their own version” but when their own devs have nothing to do because Claude is already set up to fix, merge, deploy… folks are gonna start looking for other things to do to justify their roles.
We're adding support for AGENTS.md to Claude Code.
Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md.
You can toggle this behavior in /config.
Just had a enterprise customer churn. They have vibe coded their own version to save 1000 bucks a month. I get it. It’s a lot of money for them in these vibey times, and now they can fully utilize their developers to maintain another codebase on top of their own product
Lab: Introducing Astra!
Startup: our industry harness is our moat
Lab: Introducing Astra Medical
Startup: our geographic niche is our moat
Lab: Astra Medical in Urdu!
Startup: we can do it cheaper
Lab: Astra Medical in Urdu is now Free!
Startup: feck
83K Followers 592 Followinghoneycomb, observability, the second edition of "Observability Engineering" is coming out soon. find me on substack, bsky, LI, and occasionally here. 🐝🏳️🌈🦄
7K Followers 560 FollowingWent from CTO to solopreneur, now building an empire one business at a time. Growing https://t.co/o8SD3o1h6p, https://t.co/NVUx34raAP, and https://t.co/2uIpQjuNAC
2.0M Followers 2 FollowingClaude is an AI assistant built by @anthropicai to be safe, accurate, and secure. Talk to Claude on https://t.co/ZhTwG8d1e5 or download the app.