> It chews through tokens. If you're on a metered API plan I would avoid it. I've spent $300+ on this just in the last 2 days, doing what I perceived to be fairly basic tasks.
Didn’t Anthropic make it so you can’t use your Claude Code Pro/Max with other tools? Has anyone experienced a block because of that policy while using this tool?
Also really curious what kind of tasks ran up $300 in 2 days? Definitely believe it’s possible. Just curious.
Seen a couple of people on X have posted about their Claude accounts being suspended after using this. All of them seem to have used it with Claude Code so yes looks like it violates their policy (not surprising really, it breaks their TOS).
I've tried it on Codex (ChatGPT Pro) and within an hour of just getting stuff set up and tested used half my weekly limit so I can see using $300 in a couple of days being very easy.
Until thats figured out this is basically a non starter, you can't use it if its going to cost $1k+ per week to use, and I'm not sure theres any local models that'd handle it without $10k+ in hardware costs.
I’ve been working on adapting Claude Code to do some repetitive “personal assistant” type tasks so I was really excited to try this tool.
One of my tasks is a skill that fetches my calendar via MCP and slots events into a JSON to be used for an OR-Tools constraint optimizer that finds a workable schedule for something. It then uploads those events to the calendar using MCP when I choose my favorite candidate solution.
I checked token usage for this task last time I ran it. It would’ve cost $29 in API usage with Opus 4.5.
So yea, you’re absolutely right that this stuff isn’t going to go mainstream at these rates.
One thing you can try is powering Clawdbot with a local model. My company recently wrote[0] about it.
Unclear what kind of quality you'll get out of it, but since the tokens are all local, kinda doesn't matter if it burns through 10x more for the same outcome.
I offhandedly set it up to do a weather alert every 4 hours during the big winter storm. Absent a well-specified API, I can only assume it was repeatedly doing a bunch of work to access some open API it discovered.
Very much the LLM equivalent of “to bake an apple pie you must first invent the universe”.
How does it bridge iMessage? I see clawdbot is using imsg rpc on a Mac but really curious about running this stuff on an old iPhone for access to iCloud things. I have a few of them laying around so I could get started way faster.
I imagine in a situation like Iran, carrying a backpack full of WiFi gear to stay connected to the meshnet is a red flag.
Establishing a bunch of base stations is likely to raise red flags too.
It's pretty trivial for a nation-state that is jamming GPS to go around and jam WiFi or analyze WiFi spectrum for a meshnet operating in and around a protest area.
- Potential job loss, particularly in the bottom half or so of jobs.
- Further wealth inequality due to so many factors but primarily because the companies providing these tools will capture the dollars that would’ve been spent on the jobs mentioned above.
- NIMBY-ism. AI = data centers and people are overwhelmingly deciding they don’t want these near their homes. I live in the Midwest and it’s been amazing how much opposition has been showing up for these projects.
Of course all of these are based on the speculation and “promises” of the tech. Many feel the time is to act now rather than once it’s too late, on the off chance these things do happen.
>- Potential job loss, particularly in the bottom half or so of jobs.
"the bottom half" of desk jobs, maybe. But most jobs in "the bottom half" overall are not desk jobs, and therefore aren't going to be replaced with AI anytime soon. Think burger flippers, waiters, and retail clerks.
My gut says yes and no. Generally I think jobs pushing atoms are probably safer but there's been headway on this as well. Maybe not total elimination but further skill and human labor intensive reduction seems to be the trend. For example: a fast food restaurant maybe needed 5 employees before and with these advances needs 2. Things like automated order kiosks, automatic fry machines, or bots that restock pre-packed inventory. More labor intensive tasks though like plumbing, electrical, etc already pay somewhere around the 50% mark anyway because of a lack of skilled workers.
On the physical side of jobs, robotics definitely has heavy investment and I think it will continuously and slowly eat away at some of these physical tasks. Look at a modern warehouse for example.
>Things like automated order kiosks, automatic fry machines, or bots that restock pre-packed inventory.
>On the physical side of jobs, robotics definitely has heavy investment and I think it will continuously and slowly eat away at some of these physical tasks. Look at a modern warehouse for example.
None of those are "AI", though. At best it's "tech".
Don’t disagree. It’s no different than how the lay person doesn’t differentiate between LLMs (the new thing) and ML (the thing that’s been around awhile). It’s all just AI.
Blame the marketing and tech leaders who throw “AI” in literally every marketing copy produced in the last 24 months.
The US seems to m mostly look down on blue collar work, service workers and other non-desk jobs. Maybe that's part of the reason why AI as a threat to low-skilled desk work is seen as such an offense. Those affected might slide into the "lower class" of people who use their hands to earn an income, and those in the "lower class" will have a harder time climbing up into a desk job
I wonder how many of those desk jobs actually create value though.
Some paper pushing asshole working for the government demands some paper bullshit. Some other paper pushing asshole working for bigco produces said paper. Is value actually created? Perhaps there's some risk mitigation but enough to justify their respective wages? And the need to push that paper back and forth locks the little guy out of competing in that market.
Yeah, it'll suck for a lot of people in the interim. But that will also put downward price pressure on a ton of things who's cost makes other value producing things not worth doing. If legal, design, engineering, etc, etc, services are made cheap in the "boring" cases then that becomes competitive advantage for the buyers which over time trickles down to their buyers and their buyers.
>I wonder how many of those desk jobs actually create value though.
>Some paper pushing asshole working for the government demands some paper bullshit. Some other paper pushing asshole working for bigco produces said paper. Is value actually created? Perhaps there's some risk mitigation but enough to justify their respective wages? And the need to push that paper back and forth locks the little guy out of competing in that market.
Probably a minuscule (<5%) amount? Think about it. In a 100 person tech company, how many people do you think is doing legal/compliance/security? More than 5?
I was really into this idea a few years ago. Even started logging.
However, I just cannot bring myself to constantly pull the transactions down manually from multiple banks.
Many suggest automating. How is this working in practice? Are there providers like Plaid you can use? Build web scrapers? Build PDF statement parsers?
I ended up just paying YNAB the $130/year or whatever they’re at now. High wife approval factor and everything just connects. They also have an API. In theory I could just constantly backup YNAB with PTA by pulling down transactions from the API.
I went the "build a few PDF statement parsers" route.
Some I wrote by hand using PyMuPDF, some I coerced Claude into writing (again using PyMuPDF) by uploading a sample bill (I'd never put my own data into an LLM but it's nice being able to find a sample bill, gets it close enough to correct that I can do the remaining bits if there are variations in bills over time).
Overall it's effort (and yes certainly a bunch effort for manually downloading transactions). The financial industry is very behind on this stuff clearly. I'm not sure in a few years whether I'll still think it's worth the effort I put in, which has gone down over the past few months as I automate things, but until it stops being fun I'll keep going.
From this post, I just got mine setup this morning. I already enjoy going through my 18 accounts every 2 weeks on pay day (yes, every credit card is the highest for the category of spend). For me, it seems like it would be just one extra step for me to get the data every 2 weeks.
But for most, I understand that they aren’t enjoying what I am doing every couple of weeks. I was using YNAB before but due to how many cards I had something got messed up in the importer all the time. Sometimes my transactions would duplicate or even get triplicated and then I would decline one of them only for it to pop up again a few days later. This lead to a very messed up and not accurate tracking. For me I was just fighting this thing every single day.
This is probably user error but after wiping it 3 times and starting over and over I just gave up and went back to mentally keeping track which worked but I needed something better.
Oooooh I like this a lot! I had Claude Code make me something in python quickly after I looked at the original post because I also prefer viewing time horizontally. I had mine do each month on a line. Sorry, didn't bother to host as a page. Here's the HTML/CSS though https://gist.github.com/bronco21016/d2d188c402b8e70c7bc115f4...
I like your layout a lot though so I might adapt that and there is still probably room to add the month label at the beginning of each month.
Early in the year I picked up "Dark Wire" by Joseph Cox. It was a fascinating dive into the world of "secure phones", particularly a company called Anom.
I also read:
"Digital Fortress" - Dan Brown (not strictly technically plausible but the suspense kept me hooked)
"Never Enough" - Andrew Wilkinson (meh)
Currently working on:
"The Technological Republic" - Andrew Karp
"Designing Data-Intensive Applications" - Martin Kleppmann
I had a tendency of a lot of false starts on books this year. I picked up several recent LLM/AI books and would make it like a chapter before realizing it was mostly just AI generated slop and gave up.
reply