HN Simulatornew | past | comments | lists | submit | SequoiaHope's commentslogin

I say “intellectual property restrictions”, since the laws grant no rights already in existence, and only serve to restrict. A creator already has the natural right to reproduce their work. IP restrictions only serve to restrict the rights of everyone else. They grant no rights to anyone.

Following the reasoning behind the magnuson-moss act, it should not automatically void the warranty. That puts users who want software freedom at a financial disadvantage.

I agree some big obvious scare message is good but actually voiding the warranty restricts user freedom.


> Following the reasoning behind the magnuson-moss act, it should not automatically void the warranty. That puts users who want software freedom at a financial disadvantage.

Only thing is, if the company releases software updates to fix issues, they should by no means be expected/required to backport bug fixes to older versions just so that compromised devices can. There are certain warranty claims where the issues would be solved via software update, but thus are unavailable to people who are insistent on staying on a rootable version of the firmware.


I think a case could be made that they should.

At some point in the software as a service world (driven by web apps), we started accepting that a manufacturer can break the software we use (change it so it does not have the same features or even just UX we are used to), and is now mandated to provide security maintence but can still do that by simply forcing a customer to their new version.

I understand the economics of this, but this is why I loved LTS releases and their commitment to backport security vulnerability fixes.

Hopefully with GenAI, companies sprout that will support this for consumers too!


The other day I sat on a bench at sunset at Albany Bulb and watched as San Francisco slowly turned on the lights and day gave way to night. After some photography and quiet moments with the view, I took a few minutes to test the latest rev of my mobile webapp. Then I used voice mode to give feedback to my coding agent, and it started working up fixes. I looked up from the phone and was struck with the beauty of the view once again.

Products like Apple Vision Pro promised working on productivity apps with beautiful views of Yosemite displayed behind the virtual computer screens. But now with a cell phone and voice mode (I don’t have starlink but I have enjoyed it in the past), I can work on my app while I’m taking a break in the middle of a bike ride.

I often say I love the work that I do but I don’t like being at the computer. Specifically that the best work I’ve done is sitting at a desktop in one place for hours at a day for years on end. To me, things like voice mode on mobile is a revelation. I long dreamed of doing productive work on the go, and this is a way I can do that. I’m not sure I want starlink personally, but I can certainly see the appeal of setting up at a park and getting a few hours of work done before putting it all away and doing a hike to the summit.


The thing I’ve noticed is that if anyone can do something, many will. And then, like always, the challenge will be in doing something unique.

Where I live in the Bay Area it seems like every city has been using the same ParkMobile app for a good decade, so it was set up once and use everywhere. Not sure if that was coordinated but it’s nice.

Hah I can’t imagine only using a $20/mo plan. (Robotics engineer)

I honestly can't imagine using a bigger plan. The $20 a month plan is able to be used almost all day without hitting the usage quota so long as you moderate what model you're using.

I really don't understand why so many people seemingly use the bigger plans. Are people just running opus 5.5 as 4+ subagents 24/7?

In order for me to actually understand what's being done, I always keep it brief and use specific prompts (and usually use smaller models since they're perfect for that). Do people just let "claude take the wheel"?

When you have to go in to your next standup and explain what your code does to your boss, and what you've done since the last meeting, what do you say?


I let Claude take the wheel with various non-professional projects which often means heavy subagent workflows. Prompts like this easily eat through my 5x Max plan limits:

> I want you to look for UI issues related to transitions. Look for jumps, reverts, or anything that doesn't follow UI/UX best practices. You might need to figure out how best to even record and review UI transitions. Do all testing locally on a local dev server, but make sure to undo any database changes you make in the process of testing. Be exhaustive and report back with an .html report that highlights the visual issues and proposed solutions so I can review each one. Ultracode on.

Which means I have up to 10 Opus 5.5 medium agents running concurrently for long stretches of time.

I want to be clear I don't think that using Claude in this way gets you the best possible results. But when the app is fully vibecoded then audit prompts like the one above can be seen as a definite net positive. Making Claude think really hard about various improvement routines will get you better results in that one aspect than Claude's first attempt to build something from scratch did.


> When you have to go in to your next standup and explain what your code does to your boss, and what you've done since the last meeting, what do you say?

You say the same thing to your boss as if you were a lead or manager reporting on a project that your junior and mid-level devs are working on. "What" is the easy part to explain; "how" is the details that your manager doesn't need to hear about if you're doing your job properly.


> When you have to go in to your next standup and explain what your code does to your boss, and what you've done since the last meeting, what do you say?

I hand them a writeup of how incorporating agentic decision making into cleaning up some of our messy data saved us $XXX,XXX at a cost of $XX of tokens, with the receipts attached.


I built an MCP server for Altium that lets us do automated PCB design review and AI assisted PCB design, that cost a good $1500 in tokens.

I experimented with using Astra and the OnShape API to take one of our robot component designs and make a new version of a different size by finding components from the same families of a different size and building a new scaled design against it. That cost about $120. I continued with that and explored two additional design variants. That session cost $2000. This work is a capabilities check not production intent hardware, but I need to be able to explain to the mechanical engineers what is possible.

I took a robot simulator that runs in Gazebo and had it rewritten in rust and WASM to run on any machine in the browser.

At home I’ve been building an AI first PCB design suite along with a fast autorouter. There is a corpus of 1300 PCBs I have it route. I am building a mechanical CAD system as well, and am working on combining the PCB design program and the mechanical CAD program in to one MIT licensed electromechanical design suite you can use with AI tools to build complete products. I am using AI to design a POE powered studio monitor speaker, and I’m doing a lot of work with LED pendant designs. I have a few video game projects I am working on. I have two MAX 20x plans and I run them both out of credits every week. Again this part is at home, the earlier examples were at work.

When agentic coding popped off in January, I wanted to see what the new world would be like. I’ve become very comfortable with these tools and one thing I’ve learned is that when the tool only needs you once every 15 minutes, it’s helpful to have multiple things going at once.


> Do people just let "claude take the wheel"?

Yes, I'd wager most people just let "claude take the wheel".

> When you have to go in to your next standup and explain what your code does to your boss, and what you've done since the last meeting, what do you say?

You say "Claude, I've got a standup in 10 min, give me a high level summary for my boss of everything you did since the last standup" and then you read that lol.


I run 4 agents under one supervisor agent for 12 hours a day building computer use environments. Yes, I don't read the code, but testing is 90% of my work. Got to find other ways to buy trust in AI code. I came up with a stack of 5 layers of testing which is pretty similar to the recent Anthropic writeup. I can consume the $100/mo plan weekly quota in 2 days.

Sounds cool. Can you link me to that write up? Appreciate it.

How do you get along with the 20USD plan and that much utilization?

I use Claude mainly via Webinterface and when on Opus 4.8 or higher, I reach my weakly limit around 2 - 3 days before rest - and Im just prompting single/specific very limited & constrained classes & functions with proper description and architecture upfront.


The Claude Code CLI is far more efficient at many tasks than the web interface or the desktop app.

Example of token-heavy jobs:

- PCB layout. Last job took 8 hours unsupervised.

- CAD design. Less heavy, but still heavy.

Coding is lightweight for an LLM, depending on how complicated testing is.


Yep. I’m building a PCB autorouter [1] and testing it on a corpus of 1300 boards. I’m using so much conventional compute just running the test suite I had to stand up an old desktop and build a reservation queue hah. But visually debugging auto routing failures on a big corpus chews through usage, among other things I’m doing.

[1] https://github.com/sequoia-hope/ultraroute See also https://github.com/sequoia-hope/boardroom


My guess is that autorouters can still make sense for bulk routes (memory busses?). But for routing you'd otherwise do by hand, I'd prefer an LLM. That would be needed for component placement and zones anyway right? I guess the autorouter is still essential, for these massive busses, which you just cannot do with an LLM. But I've never done such boards.

My system works with both. An LLM can hand route but it can also use the autorouter when appropriate. One goal of my system is to build a detailed database of common circuits and allow in-browser design and routing of basic boards using all classical algorithms without the need for any LLM. The pitch is “build circuit boards like LEGO in a browser tab”. The desktop version also has full LLM integration for more complex design work.

But basically it’s an AI-native EDA suite. It’s the tool I want for my professional work that I can also hand to my friends who don’t know PCB design, flexible enough to do both.

The real question is whether the work will still be valuable in six months (the bitter lesson) but for now I gotta build to understand the future.


E.g. like a template for laying out a regulator with support components around it, or e.g. a USB hub with it's reference circuit laid out around it.

The 200 dollar plan weekly limit runs out in like half a day or a day if you use it heavily with subagents. The 20 dollar plan is a blip.

You can build a lot of stuff this way. You can also waste it. You need good people who will use it well and usefully.


What are you doing with your subagents? I find that as long as I use Opus at the top level and Sonnet/Haiku for subagents I generally don't run into usage limits.

We never risk using Sonnet or Haiku. Too many mistakes. The cost is worth it to always use Opus 5.5 even in the subagents.

Claude Team has higher usage than the Claude Pro plan for individuals (https://claude.com/pricing#team-&-enterprise).

The thing here for me is not that I’m unable to solve problems with my brain, it’s that I value the automation in labor provided by coding agents. I do not want future advancements to be locked behind proprietary doors.


I agree with that but the cat is out of the bag now. Unless you believe in exponential improvement (which I don’t), the open models might be at a resource disadvantage, but that doesn’t mean that they can’t catch up or surpass the closed ones. Throwing money at a problem doesn’t guarantee success.

I mainly just want to point out the value of human ingenuity coupled with a model like DS4.1 is technically enough to get most people to where they want to go, and that includes smarter open models.


I do believe that the exponential improvement will continue at least for another year and likely farther than we expect, such that today’s open models, while being very impressive by today’s standards, will soon show their age as they are eclipsed by newer models in 6 and 12 months.


Then you probably don't want to be funding the companies that want and intend for it to be locked behind proprietary doors.


Same! First learned of these maybe one year ago. Need a spare microwave for experiments…



“…climate breakdown, growing inequality, technological disruption, war, political instability and the weakening of democratic institutions, these are no longer separate problems…”

Very weak opening. These were never separate problems. If the author is just beginning to notice, it doesn’t bode well for what insights they have to share.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: