This is something that you can bootstrap into a proof-of-concept in a day and learn the tools you like and don't like along the way.
Basically you'll use any LLM and a vector DB of your choice (I like ChromaDB to date). Write a tool that will walk your source documents and chunk them. Submit the chunks to your LLM with a prompt that asks the LLM to come up with search retrieval questions for the chunk. Store the document and the questions in ChromaDB, cross-referencing the question to the document source (you can add the filename/path as metadata to the question) and the relevant chunk (by it's ID).
Run this tool whenever your docs change - you can automate this. Being intelligent about detecting new/changed content and how you chunk/generate questions can save you time and money and be a place to optimize.
To use it, you need to accept user input, run the input as a text query against your vector DB and submit both the results (with filenames and relevant chunks) and the user's query to a LLM with a prompt designed to elicit a certain kind of response based on input and the relevant chunks. Show the response to the user. Loop if you want.
You can build most of this with as few tools as `litellm`, `langchain` and `huggingface` libraries. You'll be surprised how far you can get with such a dumb setup.
Yes, this is basic RAG. That's how you do it without getting overwhelmed with all the tooling/libraries out there.
It isn't perfect and audio occasionally de-syncs or a speaker drops out. On a dedicated wireless channel playing a local source I imagine it would be pretty solid.
Not really an option if you don't have a Mac to run Airfoil, though if you do you can use the Satellite (https://rogueamoeba.com/airfoil/satellite/) program to sync Mac your other non-Apple devices to the host.
I moved out of Australia and let my bank know that I would likely be using credit cards overseas for a while.
Sure enough, as I was trying to buy furniture for my new place, the same thing happened to me. They blocked the card and when I called them they scolded me for not letting them know that I was traveling. I told the agent that I did in fact let them know, and asked them to update the account to note that I lived overseas.
Some 5 years later I needed to use one of those accounts again. I diligently phoned the bank, let them know I lived overseas and that I was going to use the card. I used the card, the transaction was blocked, I called and was again scolded for not telling them that I went on holiday.
I swear the 'notes' they add to your account are just an eye-roll and then a call disconnect.
I started building a Magic based data science tool for 6 months before coming to the same inevitable conclusion. It sits in a Github private repo rotting away.
That will depend on things you won't know until you start.
How much do you start with, what's your burn rate, how long until you get revenue, are you bootstrapping/funding, your personal cost of living, etc.
Running a business involves risk. Risk to your comfort, your mental health, physical health, financial health, etc. Closing a business is the end of all of that, not the start.
Why do you want to scratch that entrepreneurial itch?
> If I was thinking about driving through the Amazon I would ask others what the experience was like to better understand the risks, not just hop in the car and hope for the best.
Not what you are doing.
If you were probing to discover risks, you wouldn't be here asking what happens if your business fails. You would be asking how to prevent the business from failing.
> Are you saying that the best way to handle risks is to put your head in the sand and pretend they don't exist?
When it comes to entrepreneurship, yes.
You don't know what will come along and kill your business. Maybe Meta eats your lunch. Maybe the government in your jurisdiction passes a law that is incompatible with your primary monetization strategy. Maybe your house burns down and you need to sell.
Are any of these actually worth worrying over and planning mitigation against? Or are they your own personal black swan events that you just need to handle in the moment?
You know when the best time to worry about getting a job after your startup fails? When your startup fails.
To put it bluntly, this is all about mindset. You can't de-risk starting a company. You can only believe in your ability to overcome the obstacles that will come up as they come up. Planning what happens if you fail shows enough lack of belief in yourself that you almost de-facto will fail, because that exit door is always there if things get hard.
I reached a similar conclusion, luckily before doing too much building. I'm happy with terrariums so far, they scratch my 'living things in closed systems' itch.
I've tried everything you have (except weather stations and mechanical pencils) but also make/play guitars, hobbyist electronics, paper making, painting/illustration, fixing up old cars, and MtG among others.
I realized I was being a little ridiculous when I started planning a peltier powered hydroponic cabinet for growing fresh wasabi. Most of that was to do with the disappointing results with peltier cooling temperature deltas.
The garage full of specialist tools is what kills me. I can't imagine how I'll ever use the vacuum chamber I built for epoxy stabilization again, but I have one.
I have been unofficially diagnosed with ADD (specifically without the H). My psych and I decided not to diagnose because I have coping skills and habits that prevent it from interfering too much with my life, and the long term implications of an official diagnosis in the US outweighed the improvement in my symptoms if I were medicated. I have also been officially diagnosed with MDD or whatever they call it today. Depression can display similar symptoms to ADD, and it is possible to have both which is fun for diagnosis.
I probably should have been more specific about "things you enjoy". Video games are a special case where the depressed use them as an escape, for a sense of control over their lives, and a sense of growth where there is no growth. I consider that different from hobbies - things that improve you, things that take work that you enjoy. It'd be different if you were skipping meals to finish building a model plane, but with video games you're skipping meals to prevent yourself from returning to your life.
The ADD on learning stuff resonates with me. I experienced the same thing and for myself it turned out to be a coping mechanism for depression. The jolt of dopamine I got whilst learning was compensating for a general feeling of ennui. Since being diagnosed and medicated for depression, I've found my ability to focus and stick with things long term has vastly improved, despite also having ADD.
I'd highly recommend a therapist even though the experience will most likely be frustrating to start with. Aside from the difficulty in finding one that's available, you also need to find one that you like and whose style and techniques work for you. Don't give up on the concept of therapy if your first few experiences don't feel like they work.
I've been seeing my therapist for about 4 years now and while I don't believe you're ever done with therapy, I do believe that I'm working on the fundamentals of what made me feel bad enough to seek out a therapist in the first place and that I've "debugged" most of my issues.
This is exactly the boat I'm in. I have a 1hr train commute to work that I spend skilling up in AI. I've been following the space for about 15 years and have done a bunch of self learning of earlier ML techniques (the early Stanford ML MooCs) so I'm not coming in cold. What I'm doing is:
I would agree with other commenters that recommend learning how to implement a paper. As someone who barely managed to get their undergraduate degree, papers are intimidating. I don't know half the terms and the equations, while short, look complex. Often it will take me several reads to understand the gist, and I've yet to successfully implement a paper by myself without checking other sources. But I also know that this is where the tech is ultimately coming from and that any hope of staying current outside of academia is dependent on how well I can follow papers.
I've been doing this for about a month now, and I feel I definitely understand more of the theory of how most of this stuff works and can train a simple attention based model on a small-ish amount of data. I don't feel I could charge someone money for my skills yet, but I do feel that I will feel ready with about 6 months - 1 year of doing this.
Sibling comments are mentioning undiagnosed ADD (or ADHD), I'd like to float the possibility of undiagnosed depression. The "I can't get disciplined and I'm desperate. It's hurting my job, it's hurting my home life." comment drives it home for me.
Has it always been this way for you? Do you also have problems focusing on things you enjoy?
I've experienced many of the symptoms you list for almost my entire life. I started seeing a therapist about 5 years ago and I've come to realize much of my "laziness" was actually depression. It's hard to be motivated to do the responsible things you need to do to live a life if you can't even be motivated to do fun things you actually enjoy.
You can't "fix" this alone - you're too close to the problem (and there is one, it's affecting your work and home life) to see what's wrong.
I moved into an engineering management role from IC for a year at a previous company. I also found the experience unfulfilling and wanted to move back to my old IC level.
Right around my yearly review I told my manager that I wasn't digging it. Personally I found the effort-reward loop of management to be too long, and preferred the more immediate satisfaction of releasing incremental features to be more compelling than formally mentoring and guiding the developers under me. I explained this, and my manager was supportive and helped me find a more senior IC role in a different team.
We didn't really get to have the chance to talk about management succession plans as shortly after we had a RIF and my former team was absorbed into another team and the product we worked on was put on life support instead.
I personally didn't feel any shame as I was fairly certain I didn't want to be a manager. I only accepted the role because I was pressured to at least "give it a chance" by my ex-wife who thought it was a good career move. I was apprehensive at the idea that I might have to leave to be an IC again but it turns out those fears were unfounded.
I have a devcontainer running the Cosmopolitan toolchain and stuck the cosmocc README.md in a file referenced from my AGENTS.md.
Claude does a decent job. You have to stay on top of it when it’s writing C, easy to turn to spaghetti.
Also the fat binary concept trips up agents - just have it read the actual cosmocc file itself to figure any issues out.