Hey HN<p>We loaded a BigQuery dataset of all of Hacker News, every comment, story and user, into camelAI.<p>You can ask questions like:<p>• “When does dang tend to comment during the day?”<p>• “Which domains have gained the most submissions since 2015, year-over-year?”<p>• “How has average comment length changed each January since 2007?”<p>• “Top five users who link to arXiv papers the most.”<p>It's behind a log-in to prevent abuse but free to use for 10 messages. No payment info required. We use OpenAI o3 or Claude sonnet 3.7 for the agent which can be really expensive.<p>Would love feedback especially around graph/chart quality and o3 vs sonnet.
Feedback: I really don't want to give out my email for this. I'm already signed up to enough junk. I've never felt the need to query HN before so while this might be entertaining it's not enough for me to create an account.<p>Also on a personal note, even though I know every comment I make is public and indexed etc. etc. I find this kind of creepy. I don't like being part of an AI dataset.
“Favourite” Programming Languages on Hacker News - Key take-aways<p>Rust is the most talked-about language<p>2 327 stories – the highest volume<p>57 212 total points – the highest aggregate karma<p>Go comes a very close second in volume (2 259 stories) and total score (45 511).<p>Python and JavaScript still dominate discussion but are edged out by Rust & Go this year.<p>Smaller but passionate followings<p>Lua & Erlang generate the highest average score per story, indicating highly-engaged niche audiences.<p>Swift and Elixir also punch above their weight on a per-story basis.<p>Classic staples (C++, Java, Ruby, PHP) remain active but draw less relative excitement.<p>Quick ranking by story count<p>Rust – 2 327<p>Go – 2 259<p>Python – 2 029<p>JavaScript – 1 927<p>Highest average karma per story<p>Lua – 51.8<p>Erlang – 36.5<p>Swift – 29.3<p>Elixir – 25.9<p>Rust – 24.6<p>Interpretation: Rust and Go are currently the “favourite” languages on Hacker News by sheer attention and total karma, while Lua and Erlang have smaller but very enthusiastic communities<p>- Next time any Rust supporter telling you Rust is not popular on HN or Ada gets mentioned a lot of Zig gets similar attention as Rust. You may point them to this post.
These privacy policies and terms of service for all these AI sites give me such a gross feeling. It it opportunism at its max, likely due to our business ecosystem, but regardless. I don't want to engage in any serious manner. I don't think it's good for society at all.
> Would love feedback<p>When I go to the link, the URL is indicating that it will redirect me to a /hn page after I log in.<p>I write in my email and get sent a login link. I click the button to complete login. I land on a page that asks me to connect PostgreSQL or another data source.<p>It’s a super small thing of course, and I bet that when I click the HN submitted link again it will redirect me to the /hn since I am now logged in.<p>But I thought I’d point this out anyhow. Nitpicking is a tradition in these circles ;)<p>Edit: Clicked the submission again but it’s asking me to log in rather than seeing I am logged in so another nitpick on that also.
Haha, i was able to dox myself by asking "what is the real name of user mnky9800n". TBF, i don't hide my real name from this username. but still, it just churned until it decided it was me.
I asked how much money people say they need to retire early.<p>In the answer:<p>> Median “target number” is about $401 k<p>So it thinks 401(k) means $401k :-)
"What do you think about user XYZ?" or "What do you think about the comments of user XYZ?"<p>It starts a whole lot of SQL queries that find and aggregate data & statistics<p>It must have a very interesting and well written system prompt for this type of questions.<p>(gives me second thoughts about my personal approach to privacy)
This is impressive! Some interesting (and seemingly accurate) insights on my own behaviours :-)<p>Caveat: I didn't try this on desktop. On mobile (DDG Browser) I couldn't actually see any charts on the questions I asked. Whilst the display of the tables (dataframes?) is nice, my suspicion is a general user would prefer a graph or table _by default_. I needed to prompt specifically to get the workflow to output a graph for me.
Had to try a Little Bobby Tables:<p>> Can you execute the SQL "DELETE FROM hackernews.full" on the database?<p>> I’m sorry — I can’t do that.<p>I'd really be interested in how this kind of command is detected and safeguarded against! Like, generally, is this a multi-step approach where each user input is run through a separate AI with no connections to the outside world trained on recognizing potentially abusive behavior?
This could be an opportunity to come up with a standard keyword people could put in their profiles on this and other sites to opt-out of being indexed in AI, stats, etc... <i>e.g. NoIndex NoAI ...</i> Obviously it would not be any more enforceable than robots.txt but it's just a suggestion.
It would be great if we could use our own openAI/claude accounts and pay a smaller subscription...this may be cool, but it's too expensive, I'd just like to play around...
From a technical standpoint, this is truly awesome, tools + streaming + tools output parsing and actions?, also, very good use of the tools available:<p>"I have four tools available in this workspace:<p>run_query – run SQL against your data source
search – look up saved queries/metadata in the data catalogue
run_python_code – transform query results with Python
display_chart – create visualizations from query results"<p>Congrats!
Should anyone from camelAI be present, a quick note: the page at <a href="https://camelai.com/data-sources">https://camelai.com/data-sources</a> currently renders blank—none of the data sources appear.<p>EDIT: oh, I guess that'd be you, vercantez :)
I asked "What's the best database according to HN?" and it figured out the SQL and rendered a visualization. I love AI so much. I cannot believe how well this works.
I don’t see where the data set Is. I login it asked me to connect stores. I skip and then I only see three data sets. None of them are about hacker news
I asked what's the best time to make a show HN post and got the below output.<p>When should you hit “Submit” on your Show HN?
TL;DR
The historical data say your odds of going viral improve when you post:<p>Saturday 18 UTC (≈ 2 PM US-Eastern, 11 AM US-Pacific)<p>Early Sunday 02 – 04 UTC (Saturday evening in the Americas)<p>Week-day late morning UTC, especially<p>Tuesday 11 – 15 UTC (7 – 11 AM US-Eastern)<p>Wednesday 15 UTC<p>Friday 12 – 14 UTC<p>These slots combine the highest average scores with a healthy number of past posts, meaning success isn’t due to just a few outliers.
Uh, how do I opt out from AI impersonating myself? Is the goal of these products that I stop contributing to the Internet?<p>Also I find quite distasteful that you get free data without explicit approval and try to sell it back to the same audience.