by foxfoxx 14 hours ago
For context, this is a solo project I've been building over the past year while working full-time. I've been responding as "we" in the comments since I got used to doing it other places lol
Looking for feedback and advice. I'm an engineer, not a journalist or policy researcher, so a lot of this domain is still new to me despite working on it for a year.
Love the idea. Thoughts from a UI/UX point of view, on mobile:
* Focus on the policy stuff since that's your differentiator. Put it front and center, currently it's below the "trending news". Nobody needs another trending news feed. I'd cut it entirely.
* Make your differentiator hyper-obvious at a glance on the front page. Right now your above-the-fold is dominated by a wall of AI generated text. It should include a tagline for your site and visuals that people won't get elsewhere.
* Your UI screams "vibe coded" which does not build confidence. Look to other authoritative sites for visual cues - consider a serif for headlines, make your spacing more thoughtful and consistent, reduce or remove your border radius.
Thanks! I'll look into these UX/UI ideas. As for the news, it's front and center because I want Govbase to be a site/app people regularly visit and policy does move slow. Even when a bill is introduced it can take weeks for the actual text content of the bill to show up on congress.gov. Plus on weekends/recess the government doesn't move.
I am planning to bring out more of the impact highlights from the policies to see what's "trending" or what certain reps are working on but just plans for now.
Why chase engagement? If policy is slow-moving then people can visit weekly. Or make an RSS feed. Unless you're planning to go ad monetized or worse...
There's nuance between wanting to build something people use regularly vs "chasing engagement". Even if he decides to run this as a non-profit, individuals are more likely to donate to something they use regularly and institutions are more likely to fund something with active usage. I would assume that the costs to make all these LLM-API costs are not insignificant. I agree with the previous comment that the policy is the differentiator though and hopefully there's a way to drive usage without devolving into a just another news aggregator.
That doesn't make sense to me. I don't need to "engage" daily with MSF to feel like my donation is valuable. I can go days or weeks at a time without using or even thinking much about the Internet Archive, Wikipedia, or my local classical radio station. I almost never hear or see anything about my local food bank/drive organization except when I begrudgingly check a local Facebook group and happen to scroll past a post showing off whatever community dinner they just did.
There is no legitimate reason for a project like this to prioritize a general newsfeed, as opposed to a very specific newsfeed focused on legislation, regulation activity, and court cases. I can think of many interesting and useful ways to integrate the news into a government activity tracker. Yet another slopfeed of whatever nonsense is trending in the news, is not one of them.
It's a shame because I love the idea, but I can't say I trust the creator much at all. I guess now with AI it's easy enough for me to go whip up my own.
I think if you found me on LinkedIn you'd find this comment very ironic. I'm trying to perfect "stories" more before I make them the main feed since they're the core of bringing news, policy, and social posts together.
The idea is to have ordinary people read their news with the facts and the impacts. You don't need to engage with MSF or your food bank for them to make an impact. Bringing policy impact to news does require engagement - it requires interest. This tool isn't for policy researchers and that is exactly why it's not the exact thing you described. Every day people need to use it not people starving or in a war zone.
In this case, I'd say only share news where you have some kind of structured regulatory stuff attached to it. Like sure, Trump started a war, that's noteworthy. Follow that up directly with a link out to structured tally of what reps have said, when was the last time a President did something similar, what are the relevant regulations, etc.
Rather than try to compete in the "current events" space you might have more success in more differentiated channels like having people subscribe to issues, subscribe to reps... News should be part of it but you should lead as much as possible with your differentiator. I bet you could sell enterprise level subscriptions for industry-relevant regulatory news.
This is what "stories" are which I agree will be the headline eventually but its still in development.
Hello,i don't mean to be dismissive but i think lawmaking definitely needs less AI and less pretendly-neutral summaries.
It's already a problem when researching a law proposal that dozens of news outlets will just copy-paste a bland summary of arguments from both sides, neither being explored fully.
I would recommend giving direct links to actually partisan information so people can situate the bill's intent and consequences in a broader context.
Where it helps:
- sometimes a bill's proponent is just an industry puppet whose talking points will be repeated in the media, but aren't solid enough to warrant a proper article… unlike opponents criticizing specific (for example deregulation) points
- sometimes, there are strong feelings and arguments on both sides of a bill and it makes sense to view them in their entirety; seeing one's side unhinged logic sometimes reveals more about the bill than the bill's text itself
- "same-side" opposition: sometimes a bill is perceived as "left-wing" or "right-wing" but receives opposition from the same side; for example, the democrat party is very divided on helping the rich vs taxing the rich, while the republican party is (less than 20 years ago) divided between hardcore authoritarian trumpists and libertarians defending civil liberties
All in all, i believe AI is a plight for society. We are only starting to understand the ecological and psychological costs. There are areas where machine learning can be useful (translation), but i strongly believe politics is not one of them. Please don't try to apply it to anything serious. Don't take it from me, take it from James Mickens in a talk where he explains both how ML works and how it related to the field of computer security:
https://www.usenix.org/conference/usenixsecurity18/presentat...