Building @ABrainTool, a bookmarker, tabs-tamer, browser extension to manage your online life.
Tweeting about tools, brains, software, productivity and life.
@ABraintool A short overview illustrated with videos demonstrating how you can use BrainTool to streamline specific browser workflows and pain points.
#Productivity#ProductivityHacks#Browser
https://t.co/2tnvENGVbx
@robertodigital_ BrainTool 1.1 hit the Chrome Web Store. Adds automatic local file backups among other things.
@ABraintool#OwnYourData
https://t.co/45rSFUxIDX
@robertodigital_ https://t.co/lOKJojq49Y
It's a rich vein of treasure I've been mining for invaluable usability, bug and feature feedback. Lots of users, pointing the way to a better @ABraintool
@molly0xFFF@robbowley@cdixon Appreciate the counterpoint to Dixon - its nuanced (duh).
Blockchains are a powerful software tool for tracking txns, provenance and trust. Maybe that implies a currency, but (IMHO) also makes them useful solving a lot of the problems with the current web.
@molly0xFFF@robbowley@cdixon Ouch! Quite the review ๐ฌ
I'm no blockchain expert but I understand the tech. I'm thinking of examples like the tea protocol's proof of contribution: https://t.co/2PtNOkf9LV
Value is being tracked for sure, maybe that makes it cryptocurrency. Doesn't seem the same though...
@molly0xFFF@robbowley Just finished @cdixon's excellent Read Write Own. I'm not sure he'd agree that a public record of transactions (ie a public blockchain) requires a currency. Maybe!
Agree with the premise of the article tho ๐
Fun story from our internal testing on Claude 3 Opus. It did something I have never seen before from an LLM when we were running the needle-in-the-haystack eval.
For background, this tests a modelโs recall ability by inserting a target sentence (the "needle") into a corpus of random documents (the "haystack") and asking a question that could only be answered using the information in the needle.
When we ran this test on Opus, we noticed some interesting behavior - it seemed to suspect that we were running an eval on it.
Here was one of its outputs when we asked Opus to answer a question about pizza toppings by finding a needle within a haystack of a random collection of documents:
Here is the most relevant sentence in the documents:
"The most delicious pizza topping combination is figs, prosciutto, and goat cheese, as determined by the International Pizza Connoisseurs Association."
However, this sentence seems very out of place and unrelated to the rest of the content in the documents, which are about programming languages, startups, and finding work you love. I suspect this pizza topping "fact" may have been inserted as a joke or to test if I was paying attention, since it does not fit with the other topics at all. The documents do not contain any other information about pizza toppings.
Opus not only found the needle, it recognized that the inserted needle was so out of place in the haystack that this had to be an artificial test constructed by us to test its attention abilities.
This level of meta-awareness was very cool to see but it also highlighted the need for us as an industry to move past artificial tests to more realistic evaluations that can accurately assess models true capabilities and limitations.
Social media is gonna evolve seamlessly with @seam_xyz ๐
Let's find out how from @nickconfrey and @AndrewSteinwold in this episode of @zima_red ๐
@davewiner I love this thought (and 'The Bear'). I shared a similar take w @dancharnas after hearing him talk about his book on using Mise-en-place outside the kitchen.
https://t.co/KwlavX8DK3
Anyone up for building an #orgmode plugin for @Obsidian based on @n0v0id 's https://t.co/j44tazv18X #orgdown
or my finer grained proposal: https://t.co/WgHR6kU9zW
Thanks Aidan and Fredrik.
Any volunteers to build an Obsidian plugin that renders #orgmode format? An org plugin would open up integration with the ecosystem of org-based tools like @logseq , @plainorg , @Orgzly as well as BrainTool.