To be fair, they display it reasonable prominently in GitHub when you are logged in. Given that, I feel the post title fall under the click bait category. I was fully aware of the Co-pilot opt-out change, but still clicked due the phrasing of the title.
It wasn't about keeping up. It was 100% about Google putting billions in advertising and abusing their dominance. Besides legit stuff like paying millions or more likely billions for billboards, spots in tv/radio/etc... there were monopoly "ads" on google.com, gmail,com, youtube.com homepages. And of course the classic of blocking features based on user agent alone, lying to people they need to use Chrome to access a product or a feature. They just needed to manipulate the masses and now almost everyone uses browser from an advertising company and they can keep pulling the rug.
Don't get me started. For every half-decent choice, there's a multitude of insane choices. After all this time they still don't have side-by-side review.
Equally as annoying, the break from VSCode is horrible. Having to use a separate registry, not having basic settings sync, the delay behind mainline VSCode updates.
Then, it's just plain buggier than others. The agent terminal just doesn't work semi-regularly, it doesn't like listing directories in the @, the SSH plugin crashes every other time it tries to connect, undoing agent work undoes edits I made in unrelated files sometimes. Sometimes updates just regress performance hard for seemingly no reason.
I also noticed the token use is wildly less efficient than CC or Codex these days. After almost no time at all it's up to 100,000 tokens and they're charging $1 per request for Sonnet. Side-by-side, Cursor spent $17 in the same time CC spent $4. Which is bizarre to me, since they advertise how their indexing and semantic search is more token efficient?
The autocomplete model was the only reason I stayed as long as I did. I wish there was a VSCode equivalent.
Well, the UI as a whole is ok to me (except the parts which is way too volatile). I was talking about the UX of the autocomplete model. The model are very often spot on and fast, but it's impossible to properly configure it to be less in your face. Making it basically useless for day-to-day development.
> I was granted a patent for the Slug algorithm in 2019, and I legally have exclusive rights to it until the year 2038. But I think that’s too long. The patent has already served its purpose well, and I believe that holding on to it any longer benefits nobody. Therefore, effective today, I am permanently and irrevocably dedicating the Slug patent to the public domain.
Yes, now that SDF font rendering is the industry's preference, he drops the software patent. That is, he is dropping the patent because it isn't a commercially viable piece of software, not because he is ethically opposed to it. Great virtue signaling though.
Seems more like he had the patent long enough to build a sustainable business from his own work, and now he’s been able to earn enough from it that others’ implementations aren’t a risk to him.
Which is kind of the entire point of patents, just that they last way too long relative to the speed of technological progress
He said "holding on to it any longer benefits nobody", implicitly including himself. He may believe that it's to his advantage for the patent to be more widely used.
Which makes sense--I don't doubt that he is a subject matter expert where this patent is concerned. If this algorithm continues to be widely used or its use increases, then that would be likely be good for him.
SDF font rendering was common long before Slug, and Slug is supposed to be the better solution (I haven't used it though, so cannot comment on its pros and cons vs SDF, but one obvious disadvantage of SDF is that you still need a font atlas texture, and that can get very big if you need to render some East Asian character sets).
SDF font rendering has been around 20+ years though? Valve really popularized in their 2007 SIGGRAPH paper and Chlumský developed MSDF font rendering in a 2015 thesis.
SDF font rendering was an industry standard maybe from 2007-2010. and you probably won’t believe what happened to OpenGL since then. Don’t even look into at what people are doing with GPUs these days, you won’t like it one bit!
As I'm not familiar with how Kagi is "pushing ai tools" this is mostly a comment on the framing of your question.
Are you really saying that a company specializing in search - natural language oriented at its core - should not make use of the biggest technological revolution for processing natural language?
"I remember when you could half-remember a comment from a website, type that into Google, and get taken to the article you were looking for"
It's funny to me that (to my knowledge) no browser (mainstream?) implement this functionality yet. Seems like a no brainer to index what the user have actually seen... (Could even be restricted based on viewport - I don't think it's that crazy of an idea)
I know there's a a number of third party programs which does though. Of course - multi-device being the norm - complicates things.
>It's funny to me that (to my knowledge) no browser (mainstream?) implement this functionality yet. Seems like a no brainer to index what the user have actually seen...
The answer to this is complicated.
Both Google Chrome and Microsoft Edge actually implement this. Behind the scenes, both will upload your browser history to the cloud. You can see it in network packet captures. It's implemented in the browser for the vendor, but not for the user.
The choice to not implement this for the user is very deliberate. It's contrary to the vendor's interests if the browser provides this capability directly to users. If a user's browser can take you to a website directly, then you are not using the vendor's search engine, meaning you are not looking at their ads, paid search results, algorithm, etc. It would severly impact their business model.
This is also the reason why browsers have:
- Adopted Google Chrome's "Omnibar" instead of a separate address bar and search bar.
- Implement only basic hierarchical organization for browser Favorites.
Directly and indirectly, Google is the central nexus of all modern browsers. Aside from Google Chrome, they also:
- Fund the vast majority of Firefox.
- Pay Apple for preferential treatment.
- Provide the same mechanisms to vendors who base their browsers on Chromium (i.e., Microsoft Edge, Brave).
I would love for this to not be the case. There is hope to be found in small independent browser and search companies/projects.
Never thought about this, but it makes sense they don't want a better local search, just for users to rely more on their product. It's messed up - so much time and human potential wasted on poor search and ads.
> Adopted Google Chrome's "Omnibar" instead of a separate address bar and search bar.
On the other hand, the additional tools in the Omnibar (calculator is the example most should be familiar with) makes the bar incredibly useful for random daily tasks.
Also, it seems that there is an "omnibox" API that extensions can use, which allows them to add their own tools to the omnibar/omnibox. Would be interesting as a form of "assistant" in a way.
Thank you! I was wondering why bookmarks are treated so poorly by browser, as if they are forced to include them but hate them with a passion.
That explains it. I'm a bit of a bookmark hoarder to the point where I have a local html file that holds and displays all my bookmarks and I've got that page set as my default.
It's not BS for the people who don't understand the dark patters that guide users to enabling all of this stuff. That's everyone with a Windows PC who didn't bypass the Microsoft account requirement and went with all of the defaults in Microsoft Edge. Everyone using Chrome Enterprise/Education whose Google Workspace admins don't want to get into trouble for not backing up people's stuff (i.e., sharing it all with Google). Same goes for company Windows PCs set up with Microsoft Entra ID. It's everyone with an Android device and a Google account who wants their settings backed up or transfers to a new Android device. It's in the fine print and legalese for all of these products and services.
So fwiw, browsing history shouldn’t be anywhere near that big making it unlikely there what it was. It compresses well, if they were to do it I’m sure they’d do it at regular intervals instead of a years’ worth at a time, etc.
And, of course, Firefox is open source and this wouldn’t be kept a secret.
In which case I'd love to know what it was doing sending that much data to Google IPs when I don't use Google services...
I've read all the Mozilla help pages about what automatic connections Firefox makes and it wasn't accounted for there (unless possibly something to do with SafeBrowsing.)
> Both Google Chrome and Microsoft Edge actually implement this. Behind the scenes, both will upload your browser history to the cloud. You can see it in network packet captures. It's implemented in the browser for the vendor, but not for the user.
Citation needed... (I'm talking about the page *content*, not the metadata like url and title)
There are things like Mymind (SaaS) or Karakeep (selfhosted) that do this, though they require you to explicitly save the pages instead of indexing everything by default
I would really like to see integration between Karakeep and SearXNG so that I could combine online search engine results with my self-hosted bookmarks serice.
I think the joke is that Microsoft did do something very like this -- they call it Windows Recall -- and it got a lot of angry pushback. (Partly, IIRC, because the specific way they did it initially was very bad in terms of security and privacy, but I think a lot of people quite understandably don't trust them to implement it (a) the way they claim they do or (b) competently, so even after they made a bunch of changes aimed at making it less scary it's still viewed with a lot of hostility.)
I find working more asynchronous with the agents help. I've disabled the in-your-face agent-is-done/need-input notifications [1]. I work across a few different tasks at my own pace. It works quite well, and when/if I find a rhythm to it, it's absolutely less intense than normal programming.
You might think that the "constant" task switching is draining, but I don't switch that frequently. Often I keep the main focus on one task and use the waiting time to draft some related ideas/thoughts/next prompt. Or browse through the code for light review/understanding. It also helps to have one big/complex task and a few simpler things concurrently. And since the number of details required to keep "loaded" in your head per task is fewer, switching has less cost I think. You can also "reload" much quicker by simply chatting with the agent for a minute or two, if some detail have faded.
I think a key thing is to NOT chase after keeping the agents running at max efficiency. It's ok to let them be idle while you finish up what your doing. (perhaps bad of KV cache efficiency though - I'm not sure how long they keep the cache)
(And obviously you should run the agent in a sandbox to limit how many approvals you need to consider)
[1] I use the urgent-window hint to get a subtle hint of which workspace contain an agent ready for input.
EDIT: disclaimer - I'm relative new to using them, and have so far not used them for super complex tasks.
Yes, I briefly felt like I needed to keep agents busy but got over it. The point of having multiple things going on is so you have a another task to work on.
Yes, I follow the same sort of pattern, it took a while to convince myself that it was ok to leave the agent waiting, but it helps with the human context switching. I also try to stagger the agests, so one may be planning and designing, while another is coding, that way i can spend more time on the planning and designing ones and leave the coding one to get on with it.
That's actually one of the best parts. You can trust some of the context you have loaded is side loaded in the LLM, making task switching feel less risky and often improving your ability to work on needed and/or related changes elsewhere.
reply