I like that this relies on generating SQL rather than just being a black-box chat bot. It feels like the right way to use LLMs for research: as a translator from natural language to a rigid query language, rather than as the database itself. Very cool project!
Hopefully your API doesn't get exploited and you are doing timeouts/sandboxing -- it'd be easy to do a massive join on this.
I also have a question mostly stemming from me being not knowledgeable in the area -- have you noticed any semantic bleeding when research is done between your datasets? e.g., "optimization" probably means different things under ArXiv, LessWrong, and HN. Wondering if vector searches account for this given a more specific question.
Really useful currently working on a autonomous academic research system [1] and thinking about integrating this. Currently using custom prompt + Edison Scientific API. Any plans of making this open source?
I think you misunderstood. The API key is for their API, not Anthropic.
If you take a look at the prompt you'll find that they have a static API key that they have created for this demo ("exopriors_public_readonly_v1_2025")
Just comes down to your own view of what AGI is, as it's not particularly well defined.
While a bit 'time-machiney' - I think if you took an LLM of today and showed it to someone 20 years ago, they would probably say AGI has been achieved. If someone wrote a definition of AGI 20 years ago, we would probably have met that.
By todays definition of AGI we haven't met it yet, but eventually it comes down to 'I know it if I see it' - the problem with this definition is that it is polluted by what people have already seen.
I like that this relies on generating SQL rather than just being a black-box chat bot. It feels like the right way to use LLMs for research: as a translator from natural language to a rigid query language, rather than as the database itself. Very cool project!
Hopefully your API doesn't get exploited and you are doing timeouts/sandboxing -- it'd be easy to do a massive join on this.
I also have a question mostly stemming from me being not knowledgeable in the area -- have you noticed any semantic bleeding when research is done between your datasets? e.g., "optimization" probably means different things under ArXiv, LessWrong, and HN. Wondering if vector searches account for this given a more specific question.
I don’t have the experiments to prove this, but from my experience it’s highly variable between embedding models.
Larger, more capable embedding models are better able to separate the different uses of a given word in the embedding space, smaller models are not.
> a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens
what makes this state of the art?
The tool is state of the art, the sources are historical.
First, so best in this?
Really useful currently working on a autonomous academic research system [1] and thinking about integrating this. Currently using custom prompt + Edison Scientific API. Any plans of making this open source?
[1] https://github.com/giatenica/gia-agentic-short
That's just not a good use of my Claude plan. If you can make it so a self-hosted Lllama or Qwen 7B can query it, then that's something.
I think that’s just a matter of their capabilities, rather than anything specific to this?
Nice, but would you consider open-sourcing it? I (and I assume others) are not keen on sharing my API keys with a 3rd party.
I think you misunderstood. The API key is for their API, not Anthropic.
If you take a look at the prompt you'll find that they have a static API key that they have created for this demo ("exopriors_public_readonly_v1_2025")
Is the appeal of this tool its ability to identify semantic similarity?
Seems very cool, but IMO you’d be better off doing an open source version and then hosted SAAS.
"Claude Code and Codex are essentially AGI at this point"
Okaaaaaaay....
Just comes down to your own view of what AGI is, as it's not particularly well defined.
While a bit 'time-machiney' - I think if you took an LLM of today and showed it to someone 20 years ago, they would probably say AGI has been achieved. If someone wrote a definition of AGI 20 years ago, we would probably have met that.
By todays definition of AGI we haven't met it yet, but eventually it comes down to 'I know it if I see it' - the problem with this definition is that it is polluted by what people have already seen.
I want to know what the "intelligence explosion" is, sounds much cooler than AGI.
When AI gets so good it can improve on itself
I have noticed that Claude users seem to be about as intelligent as Claude itself, and wouldn't be able to surpass its output.