For the purposes of learning, I’ve built a chatbot using ollama, streamlit, chromadb and docling. Mostly playing around with embedding and chunking on a document library.
i took a similar path, i spun up a discord bot, used ollama, pgvector, docling for random documents, and made some specialized chunking strategies for some clunkier json data. its been a little while since i messed with it, but i really did enjoy it when i was.
it all moves so fast, i wouldnt be surprised if everything i made is now crazy outdated and it was probably like 2 months ago.
It’s a bit disingenuous to have phrases like “start planning for free” when it’s basically just do qualifying questions then hit a paywall. Really needs clear pricing up front, no way to see it without trying to set up a plan. It’s also not clear what paying actually gets you (number of plans etc).
Totally agree. This is an exceptionally frustrating dark pattern. Anyone that uses it not only doesn’t deserve my money or support; they also deserve opprobrium.
(It’s not really HN‘s job, and it will probably never happen, but wouldn’t it be interesting if for every Show HN users could flag aspects of the design which would appear alongside the post title – like free vs. subscription, open source or not, presence of dark patterns, etc.)
Commitment takes effort from the customer. If you are a psychologist that studied for 20 years, I know we may not work well, but you will not bail in 1 month. If you are an entrepreneur with less experience or a coach who recently changed his vocation to become one, at least I believe you had conscious focused short-term effort. With AI/LLM you could have prototyped something in one day and I will never know how serious your intent is if there is no immediate financial or psychological return.
It feels like there’s a significant lack of “ML/AI” based approaches applied to these kinds of problems. I’ve seen a lot of example of RL/GNN papers that do attempt to solve smaller problems but it always feels like the best option is to just pay for a gurobi license and have at it. I’ve been doing some scheduling optimisation recently (close to job shop scheduling) and while there’s some examples of using RL they just don’t seem to cut it. I’ve resorted to evolutionary algorithms to get reasonable solutions to some big problems. Maybe it’s just always more efficient to using OR type approaches when you can formulate the problem well.
It depends on the problem. The security contained unit commitment problem (how you figure out which power plants to turn on when) is an unbelievably complex problem that MILP solvers like Gurobi can find globally optimal solutions (within the bounds of the MIP gap) quickly. Sure you could create a genetic algorithm, but there is no guarantee it will give you an answer that isn't stuck in a local minima. That is assuming you can make it run fast. Neural networks are also going to be sub optimal.
SAT is a standard GOFAI problem and you can of course use any programming language in the ML family to write a SAT solver. Thus I'd say that "ML/AI" approaches are, if anything, quite applicable!
I’ve been using obsidian for this for the past couple of years.
I have lots of folders and notes for work projects along with notes for learning topics. I keep track of tasks and to do lists for me and people in my team (using #people/name tags).
I have specific updates notes for each project. I add a weekly header (via a template) in reverse chronological order. Pull the key updates into that (I also have a todo for each project that pulls in tasks from all files in that project subfolder - so picks up meeting actions)
I also put them all in a canvas so when I doing updates about projects they’re all in one place.
I do the same for people I manage so I can keep track of updates and todos when I’m meeting with them.
My go to start point is a daily not where I throw in new tasks (tagged to projects or people) and those get pulled into the corresponding project/person file.
Because it’s markdown with lots of plugins it helps me do things like diagrams (mermaid diagrams) etc and excalidraw/canvas for architecting/mind map style ideation.
My Apple Watch. There are very few times where I need instant notification of things and they became distracting - I instead now just check periodically. Granted I probably don’t stand every hour anymore.
This is fantastic, smooth and really very polished. It clearly covers a lot of stuff and you’ve really got a lot covered so great work. I’ve not sat down and tried to fill out all my details as I’m worried I’ll lose all my details and have to start again. But this kind of stuff I find really interesting and most online are really bad/basic.
Main concerns are around price tbh (I’m a cheap bastard) and I think $14 a month is steep for something I’d use loads one evening and then probably use once every quarter after that.
I think the persistent storage is the key thing to make someone want to pay and the way it’s presented feels wrong to me. If I revisit the site you basically say ‘hey I’ve got all your data stored, sign up to premium and you can have it back without entering it all’ to me that comes across a bit of a ransom. I think that’s fine I’d say a couple of days/weeks have passed. But I think if you Accidentally closed the tab or it timed out it might put people off.
I think the real money maker here is likely financial planners who can pay a large fee and share/use it with their clients over zoom or whatever. Or perhaps some kind of insights/ yearly/monthly forecast summaries for a fee.
All in all amazing job, I hope it’s a great success.
Thanks for trying it out! I agree the recovery dialog needs some improvement. Ideally I'd like a way to let people back in for a limited time if they accidentally close their browser. Couldn't think of a sufficiently tamper-resistant implementation with the current architecture.. but as another commenter pointed out, maybe that's still net better(?)
Sounds like your notional usage pattern fits with how I use the tool as well, i.e. more like monthly/quarterly. If a discount or extended trial of the annual plan would be helpful, always happy to set those up as mentioned on the pricing page.
What about $5 for a one week unlock, so I can make quarterly adjustments as necessary? Or, say, $10 for a week during Q1 of the year so I can plan out my taxes for the upcoming year? (While I’m not paying the info is read-only, tempting me to play with it for $5/week.)
Currently you can do $14 for a month of access at a time. Does that scratch this itch? Or is there something about having access for even smaller windows of time that appeals to you?
The read-only idea outside of those windows is an interesting idea. I don't have a mechanism for that at the moment, but I'll consider it if some other folks express interest in this kind of plan.
Yes indeed, that'd be grand. I'm finding lots of stuff as I play with it, but after a bit I don't need (or want!) to fiddle with it regularly. A read-only option, whether free or even for a modest fee, would be ideal, especially when paired with occasional editing "unlocks" or "only-monthly/quarterly-progress-point-additions" or the like.
I wonder if the commenter who was talking about dark patterns might look at the notional implementation for this and say it feels like the tool holding your plans hostage.
I'm also curious how much you would see yourself returning to this "read-only" view. I don't imagine there would be a lot to do if you can't make changes to anything.
All good points! I mostly just don’t want my personal use to be I spend each day adjusting models. Having a thing I can check scratches some of the need for action/anxiety about the future/etc. Right now I have some complex-ish spreadsheets, and while not much changes, I find I often look at things just to feel like I’ve “done something.” And yeah, I do sometimes say “what if better market/worse inflation” and then change the values back, so I take your point well.
Yeah that kind of tinkering is what the app is made for. So it's hard not to wonder if cutting people off from that until they buy another "access pass" to their own plans might feel more frustrating than they realize.
This is what would do it for me. I make planning and big decisions once or twice a year where having write access is needed. I'd be happy to pay $14 for it.
For the rest of the year I'm just checking in from time to time to see how I'm tracking against the plan, so a free read-only mode would be ideal.
I would do $14 for a month's worth of access, and while I'm outside of those months, the data is read-only. This would let me spend ~$50/year for me to check in 2-3 times and make necessary adjustments to my financial plan.
When I'm outside those times, being able to do drive-by reviews of the data and/or show other people the plan that I've created (for validation/sharing the joy, etc.) sounds ideal.
I want to join the chorus of praise for your work, it's really outstanding! Good enough that I created my HN account after decades of lurking to praise your work. I intend to tell my own advisor that adopting PL would be a huge improvement over his current, spreadsheet-based methods for modeling my financial future. Regarding my usage pattern, I'd be glad to spend the $14 for month's access on the two or three months in a year when I might want to update my personal plans iff when I re-up it can start out using the data I persisted in previous sessions after the subscription hiatus. Does it work that way?
Thanks so much! And yep, you should be able to sign up for a month, cancel when you're done, then resubscribe later and pick back up where you left off :)
And you can always export your data to JSON too, if you prefer to have a local backup just to be safe.
Perhaps a "one shot access pass" or something that lets you in for a few months while you do financial planning may be useful.
It might also be a good opportunity to check back in with people later (say in 12 months time) and get them to sign up again, if you can provide them with valuable insights and help them stick to their plan
Do you feel like it's more the price or the billing frequency options that affect the psychology here? To me, a month of planning for the price of a cocktail sounds about right (esp. when compared with traditional advisory services), but perhaps others think in different terms. Or just disagree? haha.
Interestingly, I still get messages fairly often from new users that (in their opinion) pricing is actually too low... so I wonder if more pricing / feature tiers could eventually be helpful to appeal to the different segments.
Pricing is a super tricky issue, especially when its for something related to financials. I think there are plenty of people who wouldn't bat an eye at $14p/m (and maybe they are the target audience), but there are also plenty of people who aren't buying $14 cocktails.
I fall into the camp where I like to play around with spreadsheets (free -£time) or other online calculators (free) just to make loose projections and see where I'm at. I make a good salary (for the UK) but don't pay for any financial advice (and probably wouldn't unless my situation got really complicated). I think if it was priced at £30-50 a year or £4-5p/m I (personally) might go for premium because the tool is honestly really great!
One completely different avenue you might consider is to selling direct to companies to provide to this a service to their employees. I'm not talking financial companies, but more as part of the benefit package. My company added something to their benefits, called bippit - which is awful (or at least not useful to me), but provides virtual one-one financial advisors and some very basic online tools.
Would you fall into the camp of "make it universally cheaper"? Or carve up the feature set into more tiers with different prices? Curious how you would divvy things up, if the latter.
I do also grant general discounts on request (info on pricing page).
You're probably right about the enterprise / benefits angle, but at the moment I wouldn't have a clue how to actually go about it. Enterprise sales is the kind of thing I always imagined you might need a team (and a lot of time and pitching) to pull off... True or false?
I’m speaking as someone who has never had to price anything. To me it feels like a service that doesn’t give me monthly benefit (i.e. frequent recurring usage like my iCloud storage or Netflix etc) as I wouldn’t use it often enough, so paying monthly just feels like a waste to me. The difference between monthly rate if bought as a year and per month is pretty big to incentivise people to pay up for a full year - I personally dislike this strategy, it implies to me that I have to pay a 50% markup just to have the option to change my mind after a month or two (to me this implies I might, so best to get all the money up front).
I think you want to incentivise long term ownership of the product (MRR->YRR) with a focusing of the price at yearly. It aligns more with financial years / tax filings and the general cadence of people looking at their finances.
Now as I say I have absolutely no experience and haven’t done any market analysis. So this is just my opinion.
I think for me it's about the ongoing nature of the subscription. Everything is a subscription model these days, and I'm quite wary of "zombie" subscriptions that take money every month, but I don't actually use them.
For me financial planning feels like a "once every 5 years" process with possible lightweight annual check ins to see how I'm tracking towards the plan and tweek some details. A monthly subscription doesn't map well to this model. This is why I suggested something like an "access pass" might be a better fit for somebody like me.
The problem for me is how rarely you'd use it. I could see myself buying this, and using it forever, but only a few times a year. Monthly pricing for quarterly or semi-annual check ins doesn't feel like the right trade off. (I say this as someone who uses Actual Budget monthly).
I looked at your lifetime subscription and was keen on that for the reasons above but $500USD is eye watering.
On the other hand, mind where and who those people are. $14 is probably peanuts for a wealthy software engineer living the SV life and a 6 digit salary, so if those are the ones writing, no surprise they might think like that. Nothing wrong with making them your target audience, of course.
But in other places, $6 can already buy you a cocktail :-D
I get his point that most work that uses code is the combination of the technical structure/actual code and the creative elements that combines them in different ways. But I think it’s an act of hubris to assume AI (or whatever you want to call it) can’t, now or in the near term, do the creative part.
> Honestly, I can't believe it that here it is 2023(!!), and there still exist sites that can't figure out reliable cross-browser video playback.
Ah! I was telling myself the same thing last month (how is it possible in 2023 that things which seemed solved _years_ ago, actually still do not work?), when I was trying to watch some recording of a sport event. The site proposed several players (generally 3).
3 different computers (Linux_A, Windows_A, Windows_B).
Linux_A with browser_A: only player_A worked OK.
Windows_A with browser_B: player_A some days worked, some days didn't; player_B and player_C worked OK.
Windows_B with browser_B: player_A gave audio but no video; player_B stuttered; player_C didn't work ==> no success with this OS+browser combination
Windows_B with browser_C: only player_C worked OK;
We can note that among those combinations, we had two systems with the same OS and the same browser, and yet the behaviour was completely different.
> These sites should just give up, provide the URL to the raw video file, and let users play them back in whatever way works for them.
In general, I agree I'd also rather _not_ have web players.
However, in the specific case I am talking about, the videos were more or less 6 hours long, so I'd rather not download the whole high resolution stuff (and likely see the process fail), but be able to skip parts and/or watch/download a few parts in lower resolution and other ones in high resolution.
