A SQLite based sweeper of all the scans, notes, PDFs and images I have on my filesystem, that stores their paths and allows searching their OCR’ed descriptions and text, as provided by Mistral OCR. I can ask things like “when does my car need maintenance” or “find me that picture my kid drew for Mother’s Day”. I use pi-based bash executable to launch a doc chat like that.
https://github.com/maxim/ringbinder
Yeah, for me it was all about not letting mail and kids schoolwork pile up. I like to scan ads that local businesses leave in my mailbox, so that I can ask "show me lawn care services near me". A lot of them don't really have any other online presence.
Btw, I tried to keep the Mistral part modular, so that another OCR could be integrated.
IME way better. It may not be the best out there, but it's cheap (2c per page), fast, easy to integrate API, and sufficient for my needs. It does things like describe what's drawn in pictures and shown in graphs, which all helps when searching.
great! have you tested how well it return coordinates of objects/text? Ive tried with generic LLMs like Gemini/Qwen/Gemma and they all are unstable with coordinates around text, better when using visual grounding though
Yeah, for perfect positioning/overlaying I would be much stricter with my requirements. For that type of OCR I used Apple’s own LiveText framework that comes with MacOS. But in this use case I only care about standalone plain text and descriptive text to store in the database, not overlay over original content, so never tested Mistral on that front.
When something is that drastically different, it becomes different in kind. For example, if you have high network latency, you cannot jam (play live music) with friends remotely. If you have low latency, you can. Just because the difference is in a single value (I.e. net speed) doesn’t mean it doesn’t change the fundamental nature of what’s possible. Air travel makes the kind of business, shipping, and attendance possible that wouldn’t have been possible otherwise, because our collective lifetimes and risk tolerances are limited.
I think you're saying that there are businesses that rely on cheap air transportation that are very valuable, but at the same time couldn't afford higher air fees.
But that's a contradiction. If they are valuable, their customers would pay more for their services - that's the definition of valuable. And if their customers would pay more, they could afford higher air fees.
No, all I’m saying is that air travel is so different than any other kind of travel, that it is very special, and borderline magical. Saying something like “nothing magical about air travel, things and people would still travel around the globe” is very reductive. I’m not giving my opinion on subsidies.
Person 1. "Airline service is more valuable than people will pay for, it's a genuine force multiplier that is unaffordable without being subsidized"
Person 2. "Airlines are not magical, people and goods will move another way, so it doesn't need subsidy".
You: "Airlines are magical. Those things cannot happen another way."
There's three conclusions for what you think: 1) that airlines are special and magical and doing something which cannot be done another way, but that has no value and airlines can go away. That's incoherent. 2) Airlines are both affordable and profitable. That doesn't seem to be true and needs some supporting. 3) Airlines are doing something uniquely 'magically' valuable, they are not profitable, then they need subsidising.
Your point 3 is a non sequitur. If air travel is magical and valuable, that doesn’t automatically mean it needs subsidizing. We sometimes allow magical and valuable things to go away if we find them not to be popular enough to garner widespread political support.
My statement is correcting a fact (descriptive) not proposing what to do about it (I.e. not prescriptive).
It’s very hard to imagine what the world would look like without subsidized air travel. I have to think long and hard to figure out if subsidies would actually be sensible for something like this. I can be convinced either way right now, but it would take a lot of good historical data on something very similar, perhaps has to be specifically air travel in countries that do and don’t subsidize it, and their economic outcomes, controlled for other factors.
But saying that air travel is somehow the same in kind as other kinds of travel is incredibly shallow and reductive. We get to travel orders of magnitude faster and to places we wouldn’t even be able to reach otherwise.
Growing up in the 90s in Moscow wasn't all cakewalk (immigrated to US soon after), but I fondly remember watching the show and reading Russian-translated X-Files books. I don't know why the books were so fascinating to me. Imagined my life in America as something akin to Fox Mulder: suit, nice hair, car, hotel, official business. The lifestyle was all foreign to me, and also the coolest ever.
I'm also sticking with Sublime for many years, and at this point it feels like it is some kind of old man stubbornness (like George R.R. Martin using WordStar 4.0 type thing). I don't know why its ergonomics for me have been just unbeatable. I gave others (VSCode and Zed) good weeks and months of configuring them to my liking and using them exlusively, and always returned to Sublime. All the AI stuff just runs on the side in the terminal (iTerm2 for me, but checking in on Ghostty sometimes too, waiting on them to figure out their minimal text brightness feature).
I used vim before TextMate but TM has multiple cursors where vim has none, and I use that every day. The closest thing to that in vim is "repeat edit" but your edits need to be somewhat trivial to be repeat-able. Next is vim macros but that is too complicated already.
Everybody who says it's a 5-9-27x seems to not be aware of the obvious loophole. More like 50x increase. You were able to use over $500 worth of Opus on a $10/mo Github plan easily, no hacks. You could just prompt "plan this out for me, don't stop until fully planned, don't ask any questions", and you would get ~$5 worth of planning in one 3x request. At 100 requests/mo, each easily reaching $5, that's easy $500 worth of tokens.
So, silicon valley decides to use their playbook of expand at all costs by burning money to acquire the market (like a carcinoma), and it is the users fault ?
Should we be blamed about uber destroying the taxi business, or airbnb the hotel one? Oh sorry, "disrupting".
Uber was dirt cheap, now it is the same price as taxis, and the people working for it (the "partners", not employees) have no social benefits.
Airbnb was cheap and humane, now it is THE cause for housing crises and massive residential property "investment".
The playbook of silicon valley is destructive, not disruptive.
It is by design aimed towards wealth accumulation. The ones with most money can capture the market, and make even more. It really is late stage capitalism.
And the more wealth inequality there is, the more pain, poverty and instability will be as well. AI will only exacerbate this.
Was the business model of Uber ever a secret? What about AirBnb?
Even if we argue that we can't require from every human being to understand what they're doing, I'd still argue that there are more people who perfectly understand it and don't care than people who have no idea how such a business operates.
> You cannot expect every consumer to be fully educated and aware of the consequences of their purchasing power.
Huh? I cannot expect that people understand consequences of their actions? What are we, animals? Of course sometimes things aren't simple, and we cannot predict that using some service will create some longterm effects that in the end will be harmful. Some things are hard to predict.
But some things are easy to predict and my point is that this was exactly this case.
I mean, now we all know what Uber and AirBnb did, and we still use them because we don't care (generally speaking, I've used uber maybe 3 times in my life, AirBnb never).
No, we are not animals. But life has become so increasingly complex that is infeasible for the average person to be that invested in everything in order to have an educated opinion.
I do NOT want to have to research the business model of companies before I buy their products or services. I would like to outsource that to the government, and spend my time actually enjoying life.
Am I supposed to be invested in every change that happens around me ?
What if I am a baker, using chatGPT to experiment with recipes and develop them. Am I supposed to read about LLMs, tokens, and the silicon valley playbook ?
If you think you should not do these things, then you're a part of the problem.
If a company will advertise that they can take your oil and "dispose it legally", and then on their website they will openly write that they've found a loophole allowing them to store oil on the bottom of the ocean, then you say it's morally OK to use their services because it's legal?
If todays legislations are cargo and are being bought and sold based on the number of hired lobbyists, then you say it's OK to base our moral compas on that?
If you're a baker then you need to figure out how LLMs work at least to a level so that you could say that you've tried to figure it out, just as when I'm a software developer and I need to figure out how kidney stones work, because it might be in my own personal interest to know this.
Same thing is when buying stuff from Chinese vendors that ship cheap stuff to every corner of the world. You can buy their cheap products using your blind excuses, but then don't blame your local markets that for some unknown and unpredictable reason they closed operation.
We have brains for a reason, and we need to use this organ to fight our way through the complexity. This is the tax every one of us has to pay for being human and to live in a human world. If you want to have a brain, but decide not to use it, then I think you're just being lazy and entitled.
Sure, enshitification is my fault because I do not read the fine print, or research business models before I buy stuff.
I am not saying that the consumer has no ethical responsibilities, I am saying that is infeasible for the average consumer to do so.
> If you're a baker then you need to figure out how LLMs work
I completely disagree. I should not have to research about which types of grain are destructive to the farming industry before buying bread.
> If you want to have a brain, but decide not to use it, then I think you're just being lazy and entitled.
I have the right to choose where I spend my brain power on, and there are much, much more interesting and gratifying things to me than trying to analyse the behaviours of megacorps in order to have a fully educated decision in everything, in the this hyper complex and hyperconnected world we live in.
We disagree completely, no reason to keep repeating the same arguments. Have a nice day and enjoy reading the fine print in everything you buy, if it makes you feel better.
> Sure, enshitification is my fault because I do not read the fine print, or research business models before I buy stuff.
Kind of yes. You use it, you buy it. You create demand. And if there's demand, there's supply, economics 1-2-3. You vote "YES" with your wallet.
I read the fine print, and this allows me to NOT use Opus x30 only because it's available. I choose to not use AirBnb. I send a signal that this supply is not in demand.
And I guess because people like me read fine prints, you can feel better as well, because if something big will come up, you will hear internet rants about it, because we analyze and resist.
It sounds like you think you are saving the world one purchase at a time. Sure thing haha. And with the 5 people that read your rants, it is enough for a megacorp with millions of users to go bankrupt. Sure. Keep saving the world for us, thank you
It was going to happen regardless due to the nature of enshittification. If they really wanted to stop people using 100M tokens a day, they could've prevented it years ago.
Yeah it was crazy. Nowadays I use pi with OpenAI GPT 5.4/5.5, which to me seems both better and more generous than Claude. I supplement it with OpenCode Zen to get access to a bunch of models at token cost, and OpenCode Go ($10/mo) to get subscription-style access to Kimi, GLM and friends.
That was not my experience. When I tried to use Opus for longer tasks with Copilot, it would fill up the context completely and then crash without any output, while still consuming premium requests. (At least from September 2025 to January this year. Haven't tried after that.)
Copilot has improved immensely in 2026. I'd say to give it a try again if you're up for it. It works about as well as Claude Code these days in my experience.
Unfortunately, Opus was removed from the student plan in March. So far, I had been happy with GPT-5.3-Codex, but that model seems to have been removed this morning.
When using opencode or copilot CLI, the error messages are displayed
normally and it's possible to see what's going on. Under Pi, it
sometimes just hangs, or Pi crashes with some bun stacktrace and that's
it.
Copilot has introduced additional limits for Claude models in past
month, and it's rather easy to hit it. Pi often doesn't show anything
when this limit hits (although sometimes it shows the error, I guess it
depends on Pi version).
This was my solution to very very though compiler tests that would take sometime up to 4 hours to figure out. Some of the time would be spent on running the tests, but still... I was burning so much tokens. I have free Copilot for my open source work so I wasn't even paying the $20.
Yeah, the status page confirms this by listing CLI as a separate item from "access to passwords" and indicating it having major outage unlike the latter.
I’ve been looking at emulation for the first time in a long time, and it also blows my mind that entire big detailed games that we played for many hours take 100-400kb total (NES) or 2-4mb (Genesis).
Welcome to the world of embedded systems. They often do not have more resources that that. Even as completely new development (of pool control system or electricity meter).
I wonder if that’s it! I occasionally do some code search on GitHub and then remember it doesn’t work well and go back to searching in the IDE. I usually need to look into not the main branch because I do a lot of projects that have a develop branch where things actually happen. But that would explain so I guess this is it.
reply