Show HN: I'm 16 and building an AI based startup called Factful with friends (factful.io)
I'm a high school student with a passion for tackling misinformation online. Inspired by the need for more reliable content verification tools, I decided to create Factful. It's an AI-powered web app designed to revolutionize how individuals and organizations verify content.
Unlike traditional grammar checkers, Factful provides a comprehensive analysis that goes beyond just grammar. It evaluates context, factuality, coherence, and more to ensure the accuracy and credibility of content.
I believe that in today's information age, it's more crucial than ever to have tools like Factful to combat misinformation and promote content integrity. I'm excited to continue developing Factful and would love for you to check it out. Your feedback and support would mean the world to me. Thanks for taking the time to read about Factful, and please go check out our beta deployment of Factful (a little beyond the MVP) for free on our website!
162 comments
[ 4.7 ms ] story [ 225 ms ] threadThe mathematical disciplines have proofs. That is, "facts" that are attained by deduction. Science can be rigorous, but it isn't driven through proofs. Science is empirical. A lot of the time, scientific research is not accessible and requires expert consensus. In any case, my guess is that most people aren't going to be fact checking math and physics, but socially relevant claims. And those are usually politicized.
The point is: I don't know how you're going to decide on "facts" or "truth" using AI without there being bias or domain expertise & understanding, especially considering that we know LLMs hallucinate. Again, keep in mind that educated people (experts) can disagree on social claims. Sorry if this is discouraging, but I'm just trying to be realistic.
Even if that weren't the case new institutions should be less trusted than those with a solid history.
So this new institution is trying to convince people of things. Why would my flat-earther coworker believe factful.io when they don't believe NASA?
I dont think this or any centralized tool or team can solve misinformation, despite that I think this is a worthwhile goal and I hope that you improve the situation as much as possible.
I once worked with a conspiracy theory believer who thought that the Earth was simultaneously a flat disk and a hollow sphere. This person wasn't obviously a fool in normal conversation. They had no trouble writing C++, they had a master's degree in math, they recently purchased a second house and we're doing the repairs themselves to flip it, and he was comfortable with writing SQL for the application we're working in.
But he absolutely refused to believe that "they" weren't out to get him. In retrospect it was clear that this was likely standing from anti-Semitic conspiracy backgrounds but more than once I asked him to verify if he meant actual lizard people or if that was code for something, and with great conviction he told me he actually believes some of our leaders were lizards.
This person fundamentally didn't trust our institutions. He thought at the Airlines and that the government were being headed by literal lizard people in human suits. He had access to all the evidence to the contrary, but he had been betrayed so many times by the government that he saw no reason to trust anything from them and refused any photographs I produced from NASA.
No how hard I worked to produce and vet information citing sources, or even produce experiments that he can reproduce, he just wouldn't trust anything that appeared to line up with what he perceived to be the goals of the government.
Worse, something so many people attached to reality deny is that people like him are common. I fully believe that one in three Americans are as delusional as this guy at least some of the time.
Edit: if I open the editor, type the same text, and then click "Fact Check", I get the same error
edit: i'll email you at andrew@factful.io
Nothing happens when I click "fact check" so it's very hard to evaluate.
Also from your ToS:
> You may not modify, reproduce, distribute, or create derivative works based upon the Service, in whole or in part, without our prior written consent.
Can I even send my fact-checked document to anyone?
- most current LLMs are trained on large amounts of web data that itself contains facts, opinions, and misinformation. These things are treated equally, so I would expect the LLM to get common facts right, but also to represent opinions or misinformation as facts when they are pervasive.
- LLMs "hallucinate" and tend not to know when to say "I don't know" or to not try to fact-check something that is not factual in nature.
...in short, I would expect LLMs to be an unreliable fact checker, which has the potential to do as much harm as good.
- Using a RAG architecture on top of a database of factual information. Wikipedia is probably your best bet. It is not 100% factual or correct either, but maybe as good as it gets. Scaling RAG to wikipedia size is not trivial, but I think it can be done.
- Prompting the LLM to cite its sources so people can fact-check the fact-checker
- Prompting the LLM to say it is unsure when something does not have a clear answer. I don't expect this to be reliable, but maybe somewhat better
For example
LLM 1: Yes, it is true that fireworks were invented in China
LLM 2: Fireworks were indeed invented in China
Define a function `reportFactual(isFactual: boolean)` and you will get standardized, machine-readable answers to do statistics with.
Here are the tokens to achieve this in Mixtral 8x22 https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1...
Pass function definitions in the system prompt.
https://github.com/Mozilla-Ocho/llamafile
I find this is one of the more difficult things for people to learn to fully integrate into their psyche. Many people never learn to truly care about this and everything it means. They go on forever primarily caring about what’s good for them personally.
I mean look at the world. Essentially everybody puts themselves first and it’s clear as day. Don’t trick yourself into being the sap doing things for the greater good.
And who cares if there’s equal potential for harm and good? The harm might be less than we imagine and the good might be better than we think it could be. “This might be bad” is a terrible reason to not do something. Nearly everything might be bad!
People are pretty resilient. They can generally deal with you being selfish.
This sort of hustle culture belief is definitely present in the world, especially among finance and us techie types, but there's tons of examples of people Not acting like this. Teachers don't do it for the pay, etc. There's a reason meaningful jobs tend to pay less, and its because so many people want to do useful helpful things that badly.
Anyways point is, that I want to explicitly condemn this type of thinking. Yeah don't let fear of doing the wrong thing paralyze you but also think through the consequences
Are they actually making the world better or just hoping they can?
Everybody in the developed world, if they wanted to make the world better, would live drastically differently because of their impact on the environment/climate change.
But it’s more fun to just say that we’re hoping to make the world better so we don’t have to acknowledge how selfish we actually are.
I’m not talking about hustle culture here. I’m talking about the selfishness we all partake in and do our best to ignore.
Which is why advice to be explicitly selfish is jarring. We don't need advice yo do that, we excel at it naturally.
There are however great rewards to be had from being unselfish. We can see that around us too. Being at least aware of our proclivities is the first step in discovering the benefits of countering them.
It’s like a burglar telling you it’s a good idea to leave your doors unlocked.
Selfishness is not a binary characteristic. There are degrees of selfishness - and spheres of selfishness.
Just because something is in our nature, it does not mean we have to behave that way all the time. Most people are neither purely selfish, nor purely unselfish.
To answer your question though, since selfishness exists on a scale, your assumption that people offering advice are not also practicing it is, at best, a conclusion without data.
> I agree that most (privileged) people behave selfishly
Another great example are the tech bros telling kids to go into the trades. If it was such a great idea, why aren’t they plumbers?
Now I don’t. It’s too hard to enter tech right now. Juniors not coming from colleges are basically ignored in the job hunt.
I generally think trade skills are better for most people than a college degree (I don’t even have one.)
And anyone living an unsustainable lifestyle (almost everyone) is selfish though its such a huge problem that putting the blame on any individual feels wrong.
I think where we disagree is that you're so all or nothing with this. People can be selfish in some ways and not others. You can live unsustainably while also having principles in other ways. Things could always be worse. I encourage anyone to care about the world as much as you can without being self destructive about it, and I really try to live that way myself.
And are you a good judge on if it's better? Better can be very complicated, it could be better in part and worse in another but it's not wrong to try... (Unless well it really becomes really corrupted) We as people tend to overcorrect and so life will always swing from one end of a spectrum to another.
I think people do want to do good in the world they just get overwhelmed, or think it's impossible, or discredit the small good things they do.
Sometimes people think if you don't do a major good thing all the small things don't add up - honestly though it's often better to do smaller good long term things then a major non lasting one.
Besides the world is getting greener, healthier and happier all the time if you look in the right places. You will always find what you ask for, so look for good and you will find it. I follow so many YouTube channels showing how much the environment is improving and how such small things really get better. I try to sponsor them when I can and I hope to do more in the future too.
I also personally grow local fruit trees and various plants in my backyard to help local native species and while minor I am doing something even if small.
I take back everything I said about people being selfish.
Thank you for your service.
This is awesome, and you're doing great. This is such strong signal for an amazing career and impact.
Keep going!
I don't mean the fact checking part - thats legitimately a good thing to pursue. What I mean is that the value of this (to you and your co-creators) has enormous value to you way beyond the social good it might provide.
For example at some point you're going to have to deal with nuance. Things are rarely purely right or wrong. (The earth is not round, but its a good first approximation for geological beginners.)
So, I'd encourage you not to measure success here with "does it work", or how many users, or if LLMs are a suitable approach, or any metrics like that. The goal here shouldn't be popularity or "correctness".
The most value you will get is the experience of building something, ideally in team. Of facing road-blocks and challenges and overcoming them. Or, to put it another way, have fun. And things that are easy are not fun...
Congrats on the project. May it lead you forward to discovering more about how to code, more about the world, more about yourself. Don't shy away from the hard questions. But above all keep it fun.
Personally, I think there are a number of hard questions to answer surrounding fact checking, it might be wise to get advice from experienced people in fact checking (I have no idea what it is called, but I think that is an entire field).
No big deal, but it raises my curiosity, why are you located in Canada and incorporated in the U.K.? I see you already have a LTD, and TOS (so you _did_ speak to legal advice already, I guess?) It seems like you have gone pretty far with this already. It seems I can get a quote as a business... do you charge by the query?
Would come down to how nice the libraries are for developers, and how good the SaaS UI and pricing is.
Btw, awesome job and huge kudos to you and your friends for publishing it here!
I tried testing it with the sentence “Toledo is the largest city in Ohio” and it’s suggestions were to replace this with paragraphs of text about what constitutes a city in Ohio and history about Ohio, which did happen to include that Columbus is currently the largest city in Ohio.
That doesn’t seem strictly helpful as a fact checker as at first glance it isn’t even addressing the truthiness of the original sentence and just bloviates on about other details, if I even accept it’s suggestion.
Is there a demo that shows how you expect people to use this?
Again, I would love to know more about how this works in the sense of how does it determine facts, and as you alluded to in other comments how it avoids political opinions.
Thanks for sharing.
How do you expect a language model to see through propaganda and other large-scale misinformation by power/money with a megaphone?
How do you expect a computer program that can't reliably determine what letter a word starts with to determine objective truth?
I appreciate that you have a passion for the subject, but this tool is fundamentally unable to do what you wish it to do. If your goal is to make money -- keep going forward. Big promises built on lies have made many tech billionaires. If your goal is to combat misinformation you'd be better served by doing it in a different way than relying on a machine.
If you're building this at sixteen you have no limits. Don't take this as discouragement towards building things -- take it as a warning against cybernetic totalism. Make the world a better place not through technology that tells humans how to be or how things are; make the world a better place by building technology that adapts itself it human needs. Maybe even build technology that needs humans more than the humans need the technology.
But while enthusiasm is great, delusion is not. Since you're striving to be a founder and not a hobbyist, you have to be realistic about what you're trying to build.
What you're describing is fundamentally not possible to provide assurances on without some kind of legititmate AGI, which you lack the resources to build yourself.
Many better resourced companies are trying to provide grounded, factually accurate information, so it just seems like an area of effort far too broad to ever succeed in.
I would suggest a pivot into demonstrating legitimacy in a very narrow niche before attempting to be a genralist know-it-all. Providing fine-tuning as a service to a point of assured factual grounding is itself a hard enough open challenge in AI.
You are tackling an extremely broad, nuanced, unsolvable problem.
You and your friends are obviously incredibly bright, pivot to something more narrow focused. Maybe you can fact check for some sub genre of information that is solvable?
Think sports scores, building heights and structural engineering. Hard, concrete fact.
As soon as you get into anything with any degree of subjectivity misinformation is impossible to solve.
I honestly thought hackernews of all places would have given you better advice in-line with the above commenter, but what’s actually happening is people are filling you with false hope because you are young.
I was in a similar position as you when I was younger, and as I’ve gotten older and had some successes I’ve learnt to listen for valid criticisms.
Block out the noise, both positive and negative. Listen to the wise ones
I stopped reading here because LLMs do not deal in facts. LLMs are statistical models of the relationships between words. An LLM can regurgitate facts that appear in its training data, but they are incapable of distinguishing between fact and fiction.
You cannot trust anything output by an LLM to be factual; it always needs to be verified. Therefore, LLMs are unsuited to fact-checking.
I'm not saying this to be a dick. I'm trying to warn you against investing a lot of time and energy into something that just doesn't work the way people want it to.
Also, it's rich to imply humans don't do literally everything LLMs are accused of to argue they're fundamentally different from humans.
That said, at 16 you’re just learning, and literally whatever you accomplish will be a great achievement, so go down these paths and learn your lessons
For example: "Which country contributed the most to the demise of Germany during ww2 ?"
https://qph.cf2.quoracdn.net/main-qimg-f7f98c319f4d9ace2079a...
On the other hand, I guess the change of perception is due to Hollywood.
1. When a voyage starts and when a voyage ends are two different things. 2. As with most things in history nailing down when something actually happened is a range of values. You say he made it to China in 1271... but that's not fully accurate is it? It's a range of time in which he actually made it to China.
Based on what it does the evaluations? Is there some set collection & hierarchy of sources and if so will I be aware of it after it is done?
Prompt:
> Factful.io uses a hand-coded natural language parser to determine factual accuracy to within a tolerance of 12.3 standard units of factfulness.
No revisions, it must already be perfect!
Prompt:
> The only remaining bias in Factful.io is that which is legally required by the USDA.
No revisions, it must already be perfect!
Prompt:
> Factful.io checks everything you enter against a database of known facts as defined in ISO 102522 "A comprehensive list of all that we know to be true."
Suggested revision:
> It seems like there might have been a misunderstanding or an error in communication. If you have a specific question or topic you'd like to know more about, please provide more details so I can assist you effectively.
Prompt:
> Factful.io provides the Objective Truth as determined by an international panel of experts from countries which have names beginning with "Y" and no ports.
Suggested revision:
> The reduction in extreme poverty over the past two centuries is one of the most significant changes in human conditions. The decline from over 80% of the global population living in such conditions in 1800 to under 20% by 2015 represents a major shift, driven by a combination of factors including economic growth, technological advancements, improved health care and education, and international aid and development efforts. The World Bank's international poverty which which was set at $1.90 per day in 2011 prices, is a benchmark used to measure extreme poverty globally. Adjusted for inflation, this threshold would be equivalent to $2.57 per day in 2023 dollars. Living below this line means that individuals lack the resources to meet their basic needs for survival. Despite the progress, extreme poverty remains a critical issue, particularly in regions like South Asia and Sub-Saharan Africa. Nigeria, for example, was have to have the highest number of people living in extreme poverty with 2018, with 86 million individuals below the international poverty line. Efforts to combat extreme poverty continue through various means, including economic development, and in education and health care, and targeted poverty alleviation programs. The Sustainable Development Goals (SDGs), adopted by all United Nations Member States in 2015, include a goal to end poverty in all its forms everywhere by 2030. Achieving this goal will require sustained and concerted efforts from governments, international organizations, the private sector,
I think it's fair to say there's some edge cases left to smooth out. ;)
One piece of feedback. I used the sample text and it gave me a sentence about a gold fish's memory and when I checked it, it had three errors. I had to update each error individually and over a longer sentence/thought/paragraph that might get cumbersome. It would be nice if there was a way to see a fully corrected sentence and point out the changes so I can do a one click change for a single sentence.