Hacker Newsnew | past | comments | ask | show | jobs | submit | benlm's commentslogin

I really miss the everything is editable panel, it felt like a superpower. There’s a bit of a learning curve, but after it’s amazing and everything else feels limited.


Off topic: Fully editable AI chat conversation should really be the norm.

Editing and deleting not only your messages but also the LLM's messages should be trivial.

One of the coolest things about LLM tech is that it's stateless, yet we leave that value on the floor when UIs act like it's not.


The old one is still available! :D

Press the 3-dots menu in the upper right of the panel, and then choose "New Text Thread" instead of "New Thread".


OP here - feel free to ask any questions. We are still trying to figure out what direction to take Jumprun in from here and would love your feedback and ideas. Thanks!


If anyone was trying it out, we just had an issue with one of our backend services hitting a usage limit. All fixed now so if you had a failed refresh please try again.


We built Jumprun. You can use it to research and analyze data sources, and it'll produce beautiful canvases with tables, charts, videos, maps, etc. We're working on automations so you can setup natural language trigger conditions that execute actions.

We built it in Kotlin with Ktor server, htmx and tailwind. It uses a mixture of models, including gpt4-turbo, gpt4-vision and gemini-pro-vision. It's deployed using Kamal on bare metal.

Example canvas that provides a roundup of Apple Vision Pro reviews: https://jumprun.ai/share/canvas/01HNXB2K3GM7KPRP45Y2CVVJSC

Our learn more page with some screenshots to show creating a canvas: https://jumprun.ai/learn-more

It's a free closed beta at the moment to control costs, but let me know if you'd like an invite.


Cool! I like the "intelligent canvas" concept. Not exactly the same but my brother and I have been building a side project that also is all about making the most of a set of information using different views like maps, calendars, tables, etc. We have been looking into adding AI to make it easier to import data without having to manually tag all the data. https://visible.page


Very easy! You just need to ground it with the right data sources. Eg. you can add a web search datasource for "oculus reviews", and then add a table component to your canvas, instructing it to provide a comparative analysis.

The source material doesn't need to provide a comparative analysis itself: as long as it finds data detailing Vision Pro specs (which it already found) and Oculus specs it'll be able to do the analysis.

Canvases also have memory and auto-refresh, so once it finds the specs it can remember them across refreshes/updates, but also incorporate any new information it finds.



This is almost spooky... it produced the results of my typical google research process. Thanks for this, I'm impressed.


Just a little more context: Jumprun let's you connect different data sources (like web searches/pages, APIs, X, Youtube videos, Notion etc) and use LLMs to analyze and visualize the data.

We support rich components like tables, timeseries, charts and maps. We're working on automations at the moment so that you can provide natural language conditions that trigger actions (like sending you an email or changing updating a page in Notion).

Our long-term vision is that canvases become more interactive and interconnected, so that you end up building mini applications without it feeling like you're using a low-code app builder.


I've been a skydiver for many years and as far as I know the FAA _does_ require the pilot to wear a bail out rig. Most skydiving pilots I know do wear them, but I have come across some pilots not wearing them in flight (even though their bail out rig was in the plane next to them).


https://www.sbs.com.au/topics/voices/culture/article/2017/07...

"Homelessness then, in Australia, is more than lacking a roof over your head, it is also the absence of those features associated with “home”: permanence, security, and the freedom to come and go."

"If the world were to accept Australia’s definition and include everyone with inadequate shelter, the number would exceed 1.6 billion – roughly 20 percent of the population. Also excluded from official figures are the world’s 65 million displaced refugees in temporary accommodation."


I spent ~10 years moving about annually from apartment to apartment. It wasn't due to lack of resources. I had no sense of permanence, but I would definitely not have said that I was inadequately sheltered.


as long as you had some form of legal tenure over your resident property (this would include rental agreements and long term stays), and the property was deemed suitable by Australian standards for human habitation, you would not have been included in the homeless numbers.

merely being mobile or moving a lot is not likely enough to make you considered homeless by the Australian definition.

however, if you were mobile BECAUSE you were unable to obtain a secure residence and tenureship, or the residences you inhabited were of such a low standard that they didn't meet community standards for acceptable habitation, then you probably would.

I'm struggling to remember, but there would likely be a means/ intention component as well: so FIFO workers, mobile executives are not homeless, but couch surfing students or young people may very well be (even if they spent recent time sleeping under a roof). people camping (or glamping), grey nomads, for example, aren't considered homeless.

that being said, even if these people were counted, it's more of an argument that Australian official numbers should be even lower (though i'd recommend most people to focus of the primary/ first level homeless count for the common "popular" view of homelessness if we're going to reduce a complex phenomenon to a simple digestible stat: but it has the downside that people can then tend to misinterpret low homelessness for other arguments: say, how much poverty there is or how much social housing we need.


Received my new XPS 13 yesterday. Coil whine is very loud under high graphics load (such as watching a 4K video) to the point where you can hear clear clicking and screeching several feet away. Disabling Intel TurboBoost in the BIOS made it much quieter, but you can still clearly hear it in a quiet room. It's unfortunate, because apart from this huge issue I love the laptop.




examine.com meets google scholar

Place for all scientific studies to be elucidated with plain english explanations, analysis, information on shortcomings, links to related studies, open questions, links to further information. Would be community created content, but needs some sort of community voting/moderation system to surface the best content and empower the most knowledgable/trusted contributors.

Ideally this would be where you go when you see sensationalist headlines in popular science magazines -- here you can find out what the study actually means.

Anything like this out there?


I'm trying with http://www.sciencegist.com

The difficult part is getting contributions and building anything sustainable around this idea. You can reach me at info@sciencegist.com if you want to chat.

There's also http://usefulscience.org/ and http://sciworthy.com/ but I think they both have staff to write content.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: