I have used Claude Code in the terminal to the tune of ~20m tokens in the last month and I have very little to complain about. There are definitely quirks that are annoying (as all software has, including vs code or jetbrains IDEs) but broadly speaking it does what it says on the tin ime
> some people say that the max AI Level should be 5
> of course some people think that you lose touch with the ground if you go above AI Level 2
I really think that this framing sometimes causes a loss of granularity. As with most things in life, there is nuance in these approaches.
I find that nowadays for my main project I where I am really leaning into the 'autonomous engineering' concept, AI Level 7 is perfect - as long as it is qualified through rigorous QA processes on the output (ie it is not important what the code does if the output looks correct). But even in this project that I am really leaning into the AI 'hands-off' methodology, there are a few areas that dip into Level 5 or 4 depending on how well AI does them (Frontend Design especially) or on the criticality of the feature (in my case E2EE).
The most important thing is recognizing when you need to move 'up' or 'down' the scale and having an understanding of the system you are building
> Anyway, you’re right Claude Code is less ergonomic; generally slower.
The secret in my experience is parallelization - Cursor might be faster or have better ergo for a single task, but Claude Code really shines when you have 6 tasks that are fairly independent.
If you treat CC as just another terminal tool and heavily use git worktrees, the overall productivity shoots through the window. I've been using a tool called Ouijit[1] for this (disclosure: the dev is an old colleague of mine), and I genuinely do not think I could go back to using Cursor or any other traditional IDE+agent. I barely even open the code in an editor anymore, primarily interacting through the term with Vim when I need to pull the wires out.
Cursor can do that well too. Their code review feature usually gives a handful of independent feedbacks. I just trigger agents independently for all of those. Other integrations with Linear and Slack are also very handy to getting into this workflow. Seems like the 3.0 version is aiming at getting better at this use case.
FWIW I'm not saying Cursor is not capable of this, but that all of the 'Cursor' bits are superfluous, and using tools that bring you closer to the 'bare metal' of the terminal actually give you both more flexibility (I can run Claude Code, Crush, Codex, OpenCode, etc) and remove an entire layer of abstraction that I believe hinders a devs ability to really go all in on agentic engineering.
I started using Cursor and it was my daily driver for a year or two, but I haven't looked back once in regret moving more towards a terminal focused workflow. (Not to mention the pricing of Cursor being absolutely abysmal as well, although often comped by employers)
Oneleet (YC S22) | Multiple Roles | US & NATO Countries | Remote | Full-time
Oneleet is an all-in-one cybersecurity startup that has built its own Attack Surface Monitoring (ASM), Code Scanner, Endpoint Protection, and Compliance Platform. We recently raised a Series A and are growing at an rapid pace and working on some very exciting projects.
What we're looking for:
- Strong problem solvers who can work independently in a remote environment
- Security-minded professionals passionate about building robust, scalable systems
- Comfortable working during Eastern Time
Tech stack: Go, TypeScript, React, Kubernetes
Open roles
- Company offsites yearly (past offsites have been in The Netherlands, Portugal and Italy)
If you're interested in joining our team, please reach out to join<at>oneleet<dot>com with the subject line "HN: <Job Title>" and your resume attached.
Alternatively, you can also apply at https://jobs.ashbyhq.com/oneleet
Additional Note:
We are also building out a 'forward deployed' sales team based in San Fransisco - if interested, please reach out to join<at>oneleet<dot>com with the subject line of `HN: SF Sales`
Oneleet (YC S22) | Multiple Roles | US & NATO Countries | Remote | Full-time
Oneleet is an all-in-one cybersecurity startup that has built its own Attack Surface Monitoring (ASM), Code Scanner, Device Monitoring, and Compliance Platform. We just raised a Series A and are growing at an rapid pace and working on some very exciting projects.
What we're looking for:
Strong problem solvers who can work independently in a remote environment - Security-minded professionals passionate about building robust, scalable systems - Comfortable working during Eastern Time
- Competitive salary - Equity in a fast growing cybersecurity startup - 100% remote work - Company offsites every other quarter (past offsites have been in The Netherlands, Portugal and Italy)
If you're interested in joining our team, please reach out to samuel<at>oneleet<dot>com with the subject line "HN: <Job Title>" and your resume attached.
Oneleet (YC S22) | Multiple Roles | US & NATO Countries | Remote | Full-time
Oneleet is an all-in-one cybersecurity startup that has built its own Attack Surface Monitoring (ASM), Code Scanner, Device Monitoring, and Compliance Platform. We are growing at an unprecedented pace and working on some very exciting projects.
What we're looking for:
Strong problem solvers who can work independently in a remote environment - Security-minded professionals passionate about building robust, scalable systems - Comfortable working during Eastern Time
* Technical Sales (must have background in Computer Science or Cybersecurity)
* Invoicing Coordinator
We offer:
- Competitive salary - Equity in a fast growing cybersecurity startup - 100% remote work - Company offsites every quarter (past offsites have been in The Netherlands and Italy)
If you're interested in joining our team, please reach out to samuel<at>oneleet<dot>com with the subject line "HN: <Job Title>".
Oneleet (YC S22) | Multiple Roles | US & NATO Countries | Remote | Full-time
Oneleet is an all-in-one cybersecurity startup that has built its own Attack Surface Monitoring (ASM), Code Scanner, Device Monitoring, and Compliance Platform. We are growing at an unprecedented pace and working on some very exciting projects.
What we're looking for:
Strong problem solvers who can work independently in a remote environment - Security-minded professionals passionate about building robust, scalable systems - Comfortable working during Eastern Time
* Technical Sales (must have background in Computer Science or Cybersecurity)
* Invoicing Coordinator
We offer:
- Competitive salary - Equity in a fast growing cybersecurity startup - 100% remote work - Company offsites every quarter (past offsites have been in The Netherlands and Italy)
If you're interested in joining our team, please reach out to samuel<at>oneleet<dot>com with the subject line "HN: <Job Title>". If you have already applied but haven't heard back, feel free to follow up on the thread, things have been super busy!
Oneleet (YC S22) | Multiple Roles | US & NATO Countries | Remote | Full-time
Oneleet is an all-in-one cybersecurity startup that has built its own Attack Surface Monitoring (ASM), Code Scanner, Device Monitoring, and Compliance Platform. We are growing at an unprecedented pace and working on some very exciting projects.
What we're looking for:
Strong problem solvers who can work independently in a remote environment - Security-minded professionals passionate about building robust, scalable systems - Comfortable working during Eastern Time
Tech stack: Go, TypeScript, React, Kubernetes
Open roles:
* Senior Software Engineer (Backend)
* Security Program Manager
* Internal Security Compliance Auditor
* Technical Sales (must have background in Computer Science or Cybersecurity)
* Invoicing Coordinator
We offer:
- Competitive salary - Equity in a fast growing cybersecurity startup - 100% remote work - Company offsites every quarter (past offsites have been in The Netherlands and Italy)
If you're interested in joining our team, please reach out to samuel<at>oneleet<dot>com with the subject line "HN: <Job Title>". If you have already applied but haven't heard back, feel free to follow up on the thread, things have been super busy!
Oneleet (YC S22) | Multiple Roles | US & NATO Countries | Remote | Full-time
Oneleet is an all-in-one cybersecurity startup that has built its own Attack Surface Monitoring (ASM), Code Scanner, Device Monitoring, and Compliance Platform. We are growing at an unprecedented pace and working on some very exciting projects.
What we're looking for:
Strong problem solvers who can work independently in a remote environment - Security-minded professionals passionate about building robust, scalable systems - Comfortable working during Eastern Time
Tech stack: Go, TypeScript, React, Kubernetes
Open roles:
* Senior Software Engineer (Backend)
* Security Program Manager
* Internal Security Compliance Auditor
* Technical Sales (must have background in Computer Science or Cybersecurity)
We offer:
- Competitive salary - Equity in a fast growing cybersecurity startup - 100% remote work - Company offsites every quarter (past offsites have been in The Netherlands and Italy)
If you're interested in joining our team, please reach out to samuel<at>oneleet<dot>com with the subject line "HN: <Job Title>". Alternatively, you can also apply at https://www.ycombinator.com/companies/oneleet/jobs
I have always said that you can gain more value from self-help/life management type books by reading the table of contents and then spending the time you would have read the book just thinking about those topics and coming to your own conclusions.
This is obviously a bit hyperbole but seriously most self help books could be an article instead and I wouldn't miss anything that was cut
Yeah most self-help books start off as viral articles, popular newspaper editorals, or conference talks, and publishers will then approach the creators of these ideas and ask them to write a book about it.
The formula is simple, the idea you presented has already demonstrated itself as extremely popular. But only a thousand people can attend that conference, let's print it as a book and sell it in airports, websites, and stores around the world as a nice packaged book that everyone can buy and it will surely be just as popular but we can sell it to more people.
But then the problem. Writing down the original idea only takes a few pages, maybe 10-20. So we let the author expound a little, which brings it up to 80 pages. But still no one is going to pay $20 for an 80 page book, so the publishers ask them to break small sub-concepts into entire chapters to get to the magical 275-325 page mark that 95% of books sell at. These fit into shipping boxes well, every store bookshelf is designed around this size, even US Postal Service's "Media Mail" is optimized around this sizing.
So in the end, you are left with most self-help books being extremely padded to get to the the standard mass-market-paperback size. So books that should be long blog posts or a 15 min presentation get dragged out into 275 page epics where it becomes clear by the end that the author has ran out of stuff to say and is just filling the page count.
One great example right now is the top-selling book: "The Subtle Art of Not Giving a F$&#". I highly recommend everyone go to the nearest bookstore and read the first introduction and first chapter. They are absolute gold. The author summarizes the whole book in about 20 pages and does an excellent job. It is well written, entertaining, and enlightening. Everything you want in a good book. But then you can put the book down and walk away. Because the next 225 pages are just rehashing the same thing from the first chapter. Repeating itself. The author is clearly trying to reach the minimum 250 page count that the publisher will allow. He is grasping at straws and just re-iterating the same basic concept for 80% of the book. Sadly most self-help books are the same thing. Great concepts that need to be 20-50 pages.
reply