Dunno about that. Having used the $20 claude plan, I ran out of tokens within 30 minutes if running 3-4 agents at the same time. Often times, all 3-4 will run a build command at the end to confirm that the changes are successful. Thus the loss of tokens quickly gets out of hand.
Edit: Just remembered that sometimes, I see claude running the build step in two terminals, side-by-side at nearly the same time :D
great idea. thought about the waste of tokens dozens of times when I saw claude code increase the token count in the CLI after a build. I was wondering if there's a way to stop that, but not enough to actually look into it. I'd love for popular build tools to implement something along those lines!
hindsight is 20/20. If I'd known that Nvda, Aapl, Amzn etc. would go up, it's easy to now to regret how much money we'd have. Same thing with "RSU's" we get at FAANG. I often hear from coworkers that if they wouldn't have sold them when they got them, they'd be rich right now. Yes, they would be - but in an alternate universe, they'd have little/nothing and wouldn't have bought the car/camera/vacation they got out of the money when they sold the RSUs.
I added something related to this idea to my life-planning app: what if for projections. I track all my expenses/incomes/investments in my app. I then can with 1 click run a scenario where I move certain expenses to investments. I.e. cancelling netflix for 10 years, or xbox gamepass etc. and seeing what it would actually do to my 10 year projection (which already accounts for ETFs/Stock with variable return rates etc.). i.e.:
Exclude Recurring Expenses
Simulate cutting these expenses and investing the savings
Redirecting €19.99/month to investments
Then I see black on white what would happen if I get rid of all the 'small' subscriptions, on a visual chart. It's eye opening when one selects items that add up to a ~100 Euro ++ a month.
I tracked every single daily expense for a few years, until I hit a point where I realized I already knew exactly where my money was going and how much I could realistically save. It just comes down to discipline.
I really appreciate the idea and saved it for potential future features! My only hesitation is that adding practical projection tools might make shouldhavebought lose its fun, curious spirit and turn it into a serious financial app.
You're right of course. For me the difference maker is in seeing on a projection chart that if I just cancel 2x zwift, disney and netflix, I can save up to:
Savings from Cuts
€11,048
€60/mo @ 8%
within 10 years. That's HUGE! While the 60 Euro a month seems kind of irrelevant on its own.
Custom AI tools like these have an uphill battle to fight. Automaker[0] from webdevcody is an example of that. He, together with some other folks created an open source Agentic Coding tool (for the lack of a better term), which gained popularity on github. He was advertising/showcasing it on streams etc. A few weeks in, he posted a video[1] where he speaks about why he's not using it himself anymore and went back to Claude Code, which over time receives tools/skills/mcps/whatnot and is in the terminal which we're all familiar with.
I made similar experience. Downloaded all sorts of tools, IDE's for the new era of development. Other than claude code in cli and occasional uses of codex (because have free tokens), nothing else stuck. I can just split my terminal effortlessly how many times I want, write/speak to the terminal with any custom request etc. And once someone comes up with a clever idea on top of what claude has today, I reckon they'll add it one way or another within the next weeks.
bayesian curve meme fits here rather well:
- claude code for everything, custom IDE's/tools, claude code for everything.
Of course its not near as good, but that's not the point - it's meant to supplement normal development, not compete with it. The idea that one can be nearly as productive on a mobile phone as on a pc is a fairy tale. Best example is the github app which functionally might be ok, but is unusable for e.g. looking at the source code of a repo in any meaningful way (IMO).
There's plenty of situations where one doesn't want to stay at the PC for AI to finish its thing. Now we can just go about our life and check in from the phone. IMO great feature. Would've used it many times in the past but didn't want to be bothered with some wrapper around CC that perhaps did it already.
It's not an argument whether you can be more productive on phone or desktop. Some people (like myself) simply don't have much time to be dedicated at desks so we have to build workflows that support being able to at least be reasonably productive from our phones.
I'm super happy Anthropic finally releases this tool. It's a starting point and I hope they'll improve it. I did a comparison with its features / capabilities here: https://yepanywhere.com/claude-code-remote-control.html
I get your point, but just out of curiosity, what is 'reasonably productive' in that case? E.g. compared to speed/efficiency/ease of coding/developing/researching on PC, would you say you're 20% of that on your phone? I reckon for me the number is like <10%. Just typing code on a phone is a chore. Having browsers open on another screen, splitting terminals, ssh tunnels and so many other things make any form of using mobile phones for what I use my pc for is a literal mental pain and thus I don't do it. I'd be better off doing additional 5 minutes on my PC instead of doing 50 minutes on my phone (and I have a foldable one lol).
I know everyone is different thus my curiosity about other peoples experience!
anyone got recommendations for a 20' touch screen, auto motion enabled monitor like the skylight but to run custom software on? Most likely just a web page.
They didn't write 100k plan lines. The llm did (99.9% of it at least or more). Writing 30k by hand would take weeks if not months. Llms do it in an afternoon.
You don't start with 100k lines, you work in batches that are digestible. You read it once, then move on. The lines add up pretty quickly considering how fast Claude works. If you think about the difference in how many characters it takes to describe what code is doing in English, it's pretty reasonable.
I have no doubts that it does for many people. But the time/cost tradeoff is still unquestionable. I know I could create what LLMs do for me in the frontend/backend in most cases as good or better - I know that, because I've done it at work for years. But to create a somewhat complex app with lots of pages/features/apis etc. would take me months if not a year++ since I'd be working on it only on the weekends for a few hours. Claude code helps me out by getting me to my goal in a fraction of the time. Its superpower lies not only in doign what I know but faster, but in doing what I don't know as well.
I yield similar benefits at work. I can wow management with LLM assited/vibe coded apps. What previously would've taken a multi-man team weeks of planning and executing, stand ups, jour fixes, architecture diagrams, etc. can now be done within a single week by myself. For the type of work I do, managers do not care whether I could do it better if I'd code it myself. They are amazed however that what has taken months previously, can be done in hours nowadays. And I for sure will try to reap benefits of LLMs for as long as they don't replace me rather than being idealistic and fighting against them.
> What previously would've taken a multi-man team weeks of planning and executing, stand ups, jour fixes, architecture diagrams, etc. can now be done within a single week by myself.
This has been my experience. We use Miro at work for diagramming. Lots of visual people on the team, myself included. Using Miro's MCP I draft a solution to a problem and have Miro diagram it. Once we talk it through as a team, I have Claude or codex implement it from the diagram.
It works surprisingly well.
> They are amazed however that what has taken months previously, can be done in hours nowadays.
Of course they're amazed. They don't have to pay you for time saved ;)
> reap benefits of LLMs for as long as they don't replace me
> What previously would've taken a multi-man team
I think this is the part that people are worried about. Every engineer who uses LLMs says this. By definition it means that people are being replaced.
I think I justify it in that no one on my team has been replaced. But management has explicitly said "we don't want to hire more because we can already 20x ourselves with our current team +LLM." But I do acknowledge that many people ARE being replaced; not necessarily by LLMs, but certainly by other engineers using LLMs.
I'm still waiting for the multi-years success stories. Greenfield solutions are always easy (which is why we have frameworks that automate them). But maintaining solutions over years is always the true test of any technologies.
It's already telling that nothing has staying power in the LLMs world (other than the chat box). Once the limitations can no longer be hidden by the hype and the true cost is revealed, there's always a next thing to pivot to.
That's a good point. My best guess is the companies that have poor AI infrastructure will either collapse or spend a lot of resources on senior engineers to either fix or rewrite. And the ones that have good AI infrastructure will try to vibe code themselves out of whatever holes they dig themselves into, potentially spending more on tokens than head count.
Comments like these really help ground what I read online about LLMs. This matches how low performing devs at my work use AI, and their PRs are a net negative on the team. They take on tasks they aren’t equipped to handle and use LLMs to fill the gaps quickly instead of taking time to learn (which LLMs speed up!).
This is good insight, and I think honestly a sign of a poorly managed team (not an attack on you). If devs are submitting poor quality work, with or without LLM, they should be given feedback and let go if it keeps happening. It wastes other devs' time. If there is a knowledge gap, they should be proactive in trying to fill that gap, again with or without AI, not trying to build stuff they don't understand.
In my experience, LLMs are an accelerator; it merely exacerbates what already exists. If the team has poor management or codebase has poor quality code, then LLMs just make it worse. If the team has good management and communication and the codebase is well documented and has solid patterns already (again, with or without llm), then LLMs compound that. It may still take some tweaking to make it better, but less chance of slop.
Might be true for you. But there are plenty of top tier engineers who love LLMs. So it works for some. Not for others.
And of course there are shortcuts in life. Any form of progress whether its cars, medicine, computers or the internet are all shortcuts in life. It makes life easier for a lot of people.
Dunno. My 80k+ LOC personal life planner, with a native android app, eink display view still one shots most features/bugs I encounter. I just open a new instance let it know what I want and 5min later it's done.
Both can be true. I have personally experienced both.
Some problems AI surprised me immensely with fast, elegant efficient solutions and problem solving. I've also experienced AI doing totally absurd things that ended up taking multiple times longer than if I did it manually. Sometimes in the same project.
If you wouldn't mind sharing more about this in the future I'd love to read about it.
I've been thinking about doing something like that myself because I'm one of those people who have tried countless apps but there's always a couple deal breakers that cause me to drop the app.
I figured trying to agentically develop a planner app with the exact feature set I need would be an interesting and fun experiment.
same as you, I tried all sorts of apps. Todoist, habitica, fantastical, wunderlist, karakeep and more and more for all sorts of things. All are OK for most users, but none was GREAT for me. That's why I thought to give LLM's a proper spin. Get all the features I want, in the way I want. And anything I can come up with/see on the web over time, I can add myself within minutes instead of waiting for months for some 3rd party to perhaps add it. + No subscription fee.
While I can share the code and it might make a good foundation for forks, creating one from scratch with claude's $100 subscription will take ~2-3 weeks to get it into the state you see in the video. And that is me prompting the LLM for ~30-60 minutes most days of those 2-3 weeks.
That's awesome and a real motivator for me to try it myself. Especially since my employer is giving me a ton of credits for exploration I haven't been maximising to the point of hitting a usage limit.
Todos, habits, goals, calendar, meals, notes, bookmarks, shopping lists, finances. More or less that with Google cal integration, garmin Integration (Auto updates workout habits, weight goals) family sharing/gamification, daily/weekly reviews, ai summaries and more. All built by just prompting Claude for feature after feature, with me writing 0 lines.
Ah, I imagined actual life planning as in asking AI what to do, I was morbidly curious.
Prompting basic notes apps is not as exciting but I can see how people who care about that also care about it being exactly a certain way, so I think get your excitement.
It was when I mvp'd it 3 weeks ago. Then I removed it as I was toying with the idea of somehow monetizing it. Then I added a few features which would make monetization impossible (e.g. How the app obtains etf/stock prices live and some other things). I reckon I could remove those and put in gh during the week if I don't forget. The quality of the Web app is SaaS grade IMO. Keyboard shortcuts, cmd+k, natural language parsing, great ui that doesn't look like made by ai in 5min. Might post here the link.
Here's a sneek peak into how it looks like/what it is. If there's still appetite for the source code, I'll probably drop a gh link by the end of the week: https://streamable.com/amdz92
Op didn't say that it's incorrect. I read the article myself as well and wasn't much smarter than before. For better or worse, llms did a much better job explaining it on a high level and then giving technical details if I still wanted to know more.
I've got a moonlander as well (typing on it this very message), and while typing 'clicked' for me in general, I still miss the additional keys of a normal keyboard. I customized mine as well to match my needs, but I don't have a good spot left for '[' and ']'. Have them mapped next to 5 (right) and 6 (left) but that's just as awkward to hit as the normal position they have on the keyboard. Same with "F" keys. Having to press a modifier instead of having just another row on top is a bit meh.
Hitting ALT+F1 in intellij is gymnastics for my hands. alt is super low, modifier for F keys is on the left edge of the right keyboard, and then I need to hit "1" as well.
And there's lots of other little cuts like the ones above with the moonlander. I still enjoy coming back to my MX Master mechanical from logitech for that reason every now and then.
Edit: Just remembered that sometimes, I see claude running the build step in two terminals, side-by-side at nearly the same time :D
reply