I switched as well and I actually use the AI assistant since then primarily. It’s awesome to connect search directly with AI, almost always get what I want immediately.
I'm curious, how is the AI assistant experience different from Perplexity or even ChatGPT's search feature? Is it just the convenience of having several models there or are the outputs inherently better because the results are from Kagi's engine instead of google?
yeah, but it doesn’t need to be that way. It can be simple and makes it easier adoptable, why over engineering and reinventing the wheel of at least 2 decades experience and better practices.
OpenAI takes the backseat and wait until something stable/usable comes out of it which gains traction and takes it over then. Old classic playbook to let others make the mistakes and profit from it…
Couldn’t agree more, played the whole day today trying to get a HTTP MCP server with Claude running.
Absolutely terrible, no clear spec, absolute useless errors and/or just broken behaviour without telling what’s wrong. Reference implementations and frameworks are not working either, so only reverse engineering + trial & error until it runs, yaaay.
Feels like the early 2000 over and over again, trying to make something work.
That was a botnet, which is entirely different type of threat (i.e. not baked into the silicon by its manufacturer). Most botnets out there have at some point in their life been used for DDoS, that's one of the most common reasons to have one. (Another common reason is for use as residential proxies, for personal or web scraping use.) Botnets are usually entirely irrelevant though, nobody really jumped to accuse TP-LINK of being a national security threat when those botnets were discovered. I'm pretty sure there was even someone using the exploit to try to patch the vulnerability in as many routers as possible as a courtesy.
This story is for me a real painful death I have experienced way too many times, absolutely nuts.
But then you find an open source solution which is in general better and can do everything you want (simply tested already with just a docker compose up) but for deployment you get hit hard by compliance who just checks the SOC2 certifications and wants a in-depth due diligence of the code since everyone in the world can theoretically change it.
Then your manager asks how it can be so good if it's for free and open source.
And of course, last but not least, your overloaded team in general not happy to support just another unpredictable piece of software...
So it's the question to rather burn money and nerves with an awful SaaS offering and their endless and useless sales cycles and terrible and super expensive vendor-lock-ins or burn some money and nerves by utilising and running open source inhouse...
So typically I prefer to chose for the open source option and especially if the SaaS option isn't allowing me easy and fast self-onboarding, meaningful testing periods and a predictable and transparent pricing.
And then, if it get's widely adopted, I allocate some budget to support the authors and/or get some support plan (for more complex open source software) in place even though you most likely never need it...
Agreed, cool and certainly some improvement but Freestyle is good enough already. Next step for me is more towards the new insulin research which activates only on glucose in the bloodstream (don’t recall how it was called but was here more recently also shared). This sounded more self controlling where it’s hopefully just making sure you have enough of it in your body and don’t need to take care of the rest.
Until then, Freestyle with Omnipod Dash in a close loop with iAPS was a game changer for me: Almost no peaks anymore, HBA1c on the level of a non diabetic person…
Nevertheless, good luck in productising it and I’ll be certainly trying it once it’s available…
In my experience, the quality control isn't very good (some patches will read much more accurately than others) and accuracy isn't that good when you get out of normal ranges.
I don't think the "invasive" nature of the Freestyle is a problem at all, but it would be nice to see some innovation on either the cost or the accuracy or both.
OP lacks imagination for sure. This would reduce infections, prevent compression lows, be more discrete and potentially increase accuracy.
In no way would I describe CGM as solved, and this would go a long way towards filling many of the gaps, especially in younger / older / less compliant patient populations.
I believe this is a reference to the tech you are talking about. I have a similar take as you: current cgm tech plus closed loop is pretty good. Self activating insulin is the first promising tech I’ve seen in the 40+ years of following the research.
“Asking our governments to create laws to protect us is much easier than…”
A bit naive that, it’s too late since data is already mostly available and it just takes a different government to make this protection obsolete.
That’s why we Germans/Europeans have tried to fight data collections and for protections for so long and quite hard (and probably have one of the most sophisticated policies and regulations in place) but over time it just becomes an impossibility to keep data collections as low as possible (first small exceptions for in itself very valid reasons, then more and more participants and normalization until there is no protection left…)
It's not too late. Maybe it is for us: but in 100 years, who will really care about a database of uncomfortably-personal details about their dead ancestors? (Sure, DNA will still be an issue, but give that 1000 years and we'll probably have a new MRCA.) If we put a stop to things now (or soon), we can nip this in the bud.
It's probably not too late for us, either. Facial recognition by skull shape is still a concern, but only if the bad guys get up-to-date video of us. Otherwise, all they can do is investigate our historical activity. Other types of data have greater caveats preventing them from being useful long-term, provided we not participate in the illusion that it's "impossible to put the genie back in the bottle".
So what you're suggesting is we do whatever we can to avoid hitting 2 degrees of universal facial recognition precision? Given that the 1.5 degree target is now inevitably impossible.
Mass surveillance takes active maintenance, and most of its direct consequences cannot outlive the last of those subject to it. Alteration of the chemical composition of the atmosphere is expected to persist for millennia, with consequences that won't be felt for centuries. They're analogous only in that the same societal forces drive both: but trying to tackle those forces head-on is operating on such a high level of abstraction that you'd be wasting your time.
Start small. Get your kid's school to take the CCTV out of the toilet rooms. There's no such problem as "facial recognition" or "mass surveillance": there are many specific instances of it. Fight those.
But the Germans still ask people to register their religion, ostensibly so the government can give tax money to the relevant religion. Sorry, but the German government asking people to provide their religion to the government just reminds me of something unpleasant.
