It has been used in kagi's "quick assistant", so basically summarisation tasks (gets context from a bunch of webpages and finds the answer to a question in them, spits all the relevant to the query information, or similar).
It is great UX when you are in a search results page, but I don't use it in the assistant directly because usually this kind of speed is less relevant there.
"Summarization of what a search engine would return" is good enough for many of my purposes though. Good for breaking into new grounds, finding unknown unknowns, brainstorming etc.
I have a script that searches DDG (free), scrapes top 5 results, shoves them into an LLM, and answers your question.
I wrote it back when AI web search was a paid feature and I wanted access to it.
At the time Auto-GPT was popular and using the LLM itself to slowly and unreliably do the research.
So I realized a Python program would be way faster and it would actually be deterministic in terms of doing what you expect.
This experience sort of shaped my attitude about agentic stuff, where it looks like we are still relying too heavily on the LLM and neglecting to mechanize things that could just work perfectly every time.
Well, considering TFA, it would be pretty strange if I did!
My point was it's silly to rely on a slow, expensive, unreliable system to do things you can do quickly and reliably with ten lines of Python.
I saw this in the Auto-GPT days. They tried to make GPT-4 (the non-agentic one with the 8k context window) use tool calls to do a bunch of tasks. And it kept getting confused and forgetting to do stuff.
Whereas if you just had
for page in pages: summarize(page)
it works 100% of the time, can be parallelized etc.
And of course the best part is that the LLM itself can write that code, i.e. it already has the power to make up for its own weaknesses, and make (parts of itself) run deterministically.
---
On that note, do you know more about the environment they ran this thing in? I got API access (it's free on OpenRouter), but I'm not sure what to plug this into. OpenRouter provides a search tool, but the paper mentions intelligent context compression and all sorts of things.
Couldn't enjoy it at all. One of the first scenes shows MI6 officers, during WWII, making plans on a post-1991 world map, with reunified Germany and independent Baltic countries, etc. Kills immersion for me immediately, along with the gender politics every few minutes in a history show. Maybe I'm old fashioned.
I quit a YC-funded start-up based in Shanghai in 2016 to be nomadic for nearly a year. Stayed in 10 countries around the Pacific (Singapore, Malaysia, Australia, US, Canada etc.).
My primary take-away from the the journey is that my wanderlust is finally satisfied. After a year, I stopped moving because, travelling isn't that fun at that point. I want to build large things and have long-term relationships, which is difficult when you are a rolling-stone.
I would certainly encourage my kids to do it when they've got the opportunity. But it's likely that I wouldn't do it myself in at least a decade.
The company has an account on Bilibili[0], where its Chinese name is specified as 鲸鲮. 鲸, romanised as Jing, means "whales" (the animal). So JingOS would be "WhaleOS".
(鲮, romanised as Ling, is another water animal known as "mud carp".)
Preview can modify images. There's a button with a pencil icon that toggles a toolbar for simple image editing, such as adding lines, shapes, or texts.
I've been using the Markup in Preview since they went system-wide in macOS Mojave. (Today I learned that Markup debuted as an extension in Mac OS X 10.10 Yosemite. [0])
This comment and its children sent me on a spelunking mission and the treasures I found. Markup has a Loupe tool and Speech Bubbles.!
Such features are many, various, and somewhat obscure, akin to Easter Eggs. (Both undiscoverable and handy to know.)
My parents (who grew up in rural China in 1960s) love to talk about chopping firewood or collecting mushrooms in the forests, alone or with their siblings, when they were 8 or 10 or something. They often give me parenting advices like "don't worry about the kids; they just need one more pair of chopsticks" (as in you feed the kids and they'll take care of themselves).
