We’re trying to put together a bunch of *research ...
# two-minute-week
p
We’re trying to put together a bunch of *research tools in one place*—web search, images search, all sorts of AI thingies. It’s now possible to try some of this straight from the homepage—no login, no nothing. Please check it out if it sounds interesting at all and as always comments appreciated 🙏 Here’s a little video for your viewing pleasure 📽️ — have a great Friday and wonderful weekend!

https://youtu.be/dqwUkz7GTRE?si=JdiN0ULxxEs4VR6L

a
Hmm, first try and it attributes my work to someone else as a 'key fact' 🤔
and the second try. my fault for searching up my own projects I guess..
p
Yeah, it’s LLM based — it is hinted at during generation, but I guess it should be much clearer that’s the case and that it might be prone to some hallucination — sorry about that 🙏 Thanks for trying it out though!
a
I struggled to make it give a list of key facts that didn't contain lies, and of course they're all unsourced. Do you think LLMs have a place in research?
As it is, it seems dangerous to me.
p
With this experiment we’re trying to learn if this kind of usage pattern i.e. generating interactive initial content for a spatial workspace would be an interesting thing to explore further and what are the trade-offs. The quality of generated results could be improved even now, as e.g. the models we are using at the moment are not the best possible. Before we determine, if it’s worth doubling down on this effort we’re trading of that quality for price and speed. This generative aspect is mostly for getting you started on exploring some topic, there are other little tools and features in the app that should take you bit further. There might even an argument made that an inclusion of some more sophisticated verification tool for the generated content would be beneficial—that is the kind of thing I’m interested to learn, so thank you! I think the LLMs most likely are going to be widely used for research whether we like it or not. Given that I think it’s worth exploring the tools and interactions around them to find what’s useful, humane and fun 🙂
a
Yes sure LLMs could be useful for researchers, but I think labeling statistical jumbles as key facts isn't humane, and in the world of research will result in embarrassing retractions and probably legal issues. Sorry to be so down on this, I'm sure there are nice aspects to this work too, but I don't find it a nice experience to be presented with falsehoods like this.