Almost none of it, if you're using Claude Code. Until recently Claude only had the option of retaining memory across conversations for the desktop app.
I almost never use the desktop app, I have maybe 2-3 conversations over the last year that have nothing to do with my job. Opus (and now Fable) genuinely do seem to "understand" what you intend based off what you're explaining a lot better than other models I've tried.
Gemini gets close in some cases, but it falls over in the actual implementation sometimes. I haven't tried Kimi yet but MiMo isn't too shabby either.
I'm not sure they can actually respect that 30 days absolute commitment. Let's say some internal tool flags a suspect conversation, it bubbles up and a human operator reads it and it looks like evidence of a crime. Then, that employee is legally bound in many jurisdictions to prevent the destruction of that piece of evidence.
It's one thing to commit to a "everything is deleted when you press delete" automatic policy. It's quite another to say "we'll keep some stuff for up to 30 days, look inside it for any malfeasance, then pinky promise we'll delete it".
It generally goes without saying that legal obligations must be met. Before this 30 day policy they already had to comply with subpoenas and government retention requests.
Same with CSAM policies for any cloud provider. Doesn’t matter what the retention policy says, if the law says otherwise, the law wins. And there is no obligation to spell out every law in every country that might change how data is handled.
It's probably been updated several times (why does it even matter what it says now if they can update the terms at will), but now it says:
> After 30 days, the data is deleted automatically, except in the rare cases where it's part of a safety investigation or we're legally required to keep it.
They write "We will require 30-day retention for all traffic on Mythos-class model". For potentially criminal content, maybe it's not "we", but "the authorities" that require the retention?
... and now I wonder if "we require retention" leaves the door open to retention that is not required, but let's say convenient.
> Prompts and model completions are retained for at least 30 days and then automatically deleted, unless they are subject to a safety investigation or we are legally required to maintain them.
That's strange. Even in my hobby-toy app, I have a TOS that I bump whenever the terms meaningfully change, and in my app, it forces a re-acceptance of the new terms before using the app again.
> After 30 days, the data is deleted automatically, except in the rare cases where it's part of a safety investigation or we're legally required to keep it.
Yep. They changed the terms, which needs legal review in my org, but the Fable model was available immediately, so of COURSE people have to go and flock to it to see how much better it is. Amazing how easy it is to spend five figures on demand and have very little to show for it; meanwhile when I want to buy a piece of enterprise software for 40-50k/year I have to spend weeks or months building the case, providing justification for ROI etc.
Depending on what you mean by "school" I'd disagree. Voluntary tertiary education makes sense, not all chosen professions may need or benefit from a degree.
But primary education needs to be a requirement for every child. Coming from a country with a large illiterate population, it's easy to see how hard their lives are compared to folks with an education but similar socio-economic backgrounds.
Now obviously implementing universal primary education and the details can be debated and need to be context specific.
Problem is when one mixes kids who don’t want to be there with one’s that do, they all suffer.
Makes a lot of teacher not want to be there too!
The schools also have little interest in spending time and money on the higher performing students. They teach the minimum and focus resources on the failing ones to raise school averages.
Currently, tertiary education is where a lot of real learning takes starts to happen.
> tertiary education is where a lot of real learning takes starts to happen
Hilarious assertion.
Absolutely false in my experience.
Someone who just starts to learn in college will be years behind the students who began in high school. They probably mistake it for not “being good at” a subject, but it can really keep people away from some areas. For example, hard sciences and math, where years of training problem solving skills makes solving new problems easy.
Not saying all primary/secondary education is good, but there is a massive gap between the good and the bad.
I mean more that the elementary/secondary school years are largely wasted in terms of what could have been taught.
Yes, some things are taught and sometimes learned, but only superficially.
Even basic economics and financial literacy is taught way too late. These kids have been ogling phones, tablets, apps since they were in Kindergarten and then learn a few basics over a decade later?
Acceleration in Physics is not a difficult concept. Yet, it’s often taught late in secondary school - 6 to 8 years after teaching fractions.
Each year Math classes largely repeat the previous year with just a small extra wrinkle (except for the crazy year known as Geometry).
Pre-algebra, algebra I, algebra II, advanced math, Calculus I. That’s 5 years to poorly learn lines, parabolas, and integrals — longer than an entire college education.
Imagine if we taught grammar that way. All
Of Elementary education would be stuck in the simple tenses! The future perfect continuous would be taught Senior year!
I’m not advocating teaching Calculus in 2nd grade but I think we should be doing better.
> Currently, tertiary education is where a lot of real learning takes starts to happen.
The phrase "real learning" is hard to define but I think I understand what you mean here, ie critical thinking. But this is only possible on the back of foundational literacy possible by years of primary education.
> Problem is when one mixes kids who don’t want to be there with one’s that do, they all suffer.
Kids that "don't want to be in school" need to be treated with care and shown the value of education. Not ejected out of the system to protect teachers. The kids might not want to be there for a variety of reasons, but if you've ever interacted with kids informally you'll know they are typically curious and eager to learn about the world around them.
And if they aren't the reasons need to be understood and the kids would ideally be provided the care they need, although there reality is far more complex.
This exception does not invalidate the basic premise of primary education, the benefits of which can be seen globally in pretty much every context.
> Kids that "don't want to be in school" need to be treated with care and shown the value of education.
I have yet to see a suggestion on how to do that, that isn't obviously unworkable.
> Not ejected out of the system to protect teachers.
It is not teachers I worry about, it is the other students. Peer pressure matters and so put kids who want to be there with kids that don't and some kids will decide they don't want to either. (the reverse is also true, but there is no way to know and I wouldn't risk my kids who like school in an area where many kids don't want to be there)
Yep that's definitely fair, to not want to put your kids in a school which has a large population of troubled children.
But to the original point I was trying to make, troubled kids don't automatically mean they don't deserve education or we should allow them to fail out or give them the option of leaving primary or secondary education. We should really be making every attempt at figuring out ways to make them stay in school, given how stark the difference in outcomes are.
And why they don't want to be there? This unearths more complex topic of individuality in aproximating school, because I think every kid wants and does't want different things. And these aren't limited to school material but also include social dynamics between peers or even type of chairs (ask kids with ADD spectrum).
If it was up to me (back then), I wouldn't have even done primary school. I'd wager that the vast majority of kids wouldn't want to do school, because obviously, but that's why we don't let kids make important decisions like those for themselves.
Looking back I am extremely appreciative of my time in school as much as I might've not liked it at the time, and my education has undoubtedly made me into a more intelligent and capable person in pretty much every conceivable way. Especially high school, pretty much everyone I know who's a high school dropout (and doesn't come from a wealthy family) is much worse off than their peers who finished it.
As for tertiary education, that is already completely optional. I attended university for 1 year, said "This ain't for me", and things worked out just fine for me.
I don't like my options. I want all kids to like school and so be there from 6 - 26 (that is get a phd). Anything else is a failure, even if it makes some kids better to get rid of other kids, it makes those kids worse.
Leaving school after 8th grade used to be pretty common. Many jobs were available for someone with an 8th grade education, or you'd start an apprenticeship.
If we are talking about the US, most (all?) states have a separate type of high school for people who plan to pursue the trades. You don't need to leave school.
The upper division has and is getting an education always has and always will and the same applies to those with money, with the screw worm fly hitting Texas of recent measles is ok fame and the current administration which is the worst in American history run by imbeciles the can do America appears to be gone and education for most along with it.
Academic writing is surprisingly hard. Distilling months or years of work into its essential ideas is almost as challenging (for me anyway) as the research itself.
Often it forces a clarity that only comes from writing ideas down in a way that's necessary to explain your results to your peers.
The process itself sucks, but the outcomes are often quite satisfying and rewarding.
I admire the old papers.
"In this manuscript we derive XYZ from ABC and show that EFG still holds"
followed immediately by something akin to "We begin by showing ... "
Nowadays the intro/motivation/problem statement / related work (citation tax) / formulation/<actual results> / simulations / conclusions / futurework format is just soul crushing.
Old papers were essentially essays. When there were fewer researchers publishing fewer papers, you were expected to read everything relevant you came across. It made sense to optimize the papers for reading.
Today there is much more research being done and published, and fully reading a paper is a special case. Papers are now more structured, and the primary use case is quickly skimming over the paper to determine if it merits more thorough reading. (Usually it doesn't.)
Maybe! But also maybe niche research can just be for the niche researchers. The work is funded, and therefore the "why" hoops have been jumped through, right?
And anyway, aren't reviewers themselves supposed to be able to connect dots?
When I was an active reviewer I tried not to ever say "Who cares" in so many words and just focus on the technical contributions. There's enough overinflation/fraud in papers that we dont need to be encouraging it by asking them to over-over inflate a possible reason for the work that is beyond the obvious ones that reviewers in the same field would appreciate.
This is true for a direct democracy, but for a representative democracy like the US (and many other countries) there's more nuance. Combined with first past the post voting, there's a lot of room for suppression of voices that are not aligned with those already in power.
For say something like the state legislature race in a state, they count up all the seats they have won in each district, and whichever party has won the most seats wins the race. Voters are therefore put in buckets (districts) and their votes are counted in aggregate.
This allows a process called "gerrymandering" to redraw district boundaries arbitrarily. So if there is say a democratic-party majority voting bloc in a particular area, I can redraw the surrounding districts to split that geographic area into many parts, so their votes get split across multiple districts and hence "diluted".
The voting rights act asserted this is a form of voter suppression. Specifically related to black voter suppression, if a state is say 40% black by population and they have no black representatives, it warrants a closer look as to why.
I hope that wasn't too confusing of an explanation. I'm not from the US but I'm quite interested in these things.
You explained it well. Representative democracy complicates systems of fairness since it adds another layer that itself also needs to be fair. And each is an opportunity to be corrupted into unfairness.
Our education curriculum is also a big problem here. If I stopped random people on the street in the U.S. and asked them what first-past-the-post is, I suspect only a small number would be able to answer.
Yet people are baffled as to why we have the two party system, gerrymandering, and all of the other problems. You can’t fix what you don’t understand. We have to start there.
Ranked choice is starting to gain some traction in the U.S. But there are many different ranking methods and the one we are using is instant-runoff, which has many of the same problems as first-past-the-post, including polarizing candidates and winners. I think if these systems were more broadly understood, many people would prefer Schulze for its fairness properties and to reduce polarization.
"Parasitic compute" is strange way to describe "a user running dev workflows on their own GitHub Actions allocation"
when you run ghost, it creates a "ghostbox" - an ephemeral machine on your GitHub account, on your GitHub actions minutes, accessible only by your SSH identity. It's orchestration around GitHub's infra.
Proprietary software built on GitHub is not exactly an unusual category.
I don't believe in releasing source anymore after years of doing it. It's closed source, Rust binary, proprietary but free software offered as a utility. It's the same patterns as used by coding agents and many other CLI tools.
So, your threat model is that I’m really building my business and reputation by creating illegal, criminal malware? Ponder that, is that really a plausible thing to you? You think that about me?
No, I only use open source agents, weird of you to assume that I would make an exception just for agents. My threat model is that trust is earned, not given away to complete strangers who act hostile to simple inquiries.
I was sincerely interested in why you were choosing closed source, you decided to take it as an attack.
lol No, I didn’t take it as an attack (tho that's what it was) i just didn’t answer your question. If you’re not okay with that i guess you’ll need to figure that out yourself.
That’s where i was going with my reply - i wanted you to think more about it. You perceived it as hostile but really I was just asking you some questions, simple ones. It does seem like you’re projecting here, maybe consider that more.
Because even tho I didn't take it as an 'attack' it was an attack, really. Think: What are you saying: you don't trust some software that I wrote. What does that mean? That means you think it's going to do something bad. That means you think I'm going to try to do something bad to you, by this beautiful creative effort that I'm putting out. Like wut? You really are not a builder if you don't understand how that feels, for me, but also -if you don't see the problem with just thinking that's what I'm going to do, like that's crazy. Like you think it's okay to just accuse me of that, just casually, like what? And then you don't think I can saying anything about that - because otherwise I'm taking it as an attack. Which is what it was. So of course I'm going to say something, and I can. And if you don't like that - maybe think more before you accuse people of what you're just projecting.
So, I took it as ignorance, which is what it is, I assume, which is why I asked you questions. Because if I was going to give you my real answer, I don't think you would understand it. That's why I didn't answer your question, because I didn't feel you'd understand (why might that be? Because you just fake accused me of trying to do something I'm not doing?). Is that not obvious to you?
Anyway, what else were you saying? Not weird about agents, it’s so common. I guess you’re a little unusual in your fastidiousness about that. But that’s not a problem.
What about apps on your phone, are you okay with that? Or you have, like, a dumb phone?
If you do want to know my views on open source, maybe you can try your empathy and tell me why you think?
It’s okay if you don’t want to. I’m finding the interaction with you a little boring… lol
Ah, so very considerate of you, well someone's read it, but the short version is: you have 0 right to attack or accuse me in any way. The fact that you want to, just shows you're a bad perosn. You're wrong. You assumed I'm doing something bad, but you don't know me, you tried to blame me for your prejudice, but that's just you, projecting, crazy.
"Why do you want to protect your IP/time/effort rather than giving away your source code? I don't run binaries as a general rule, nothing to do with ghost, which looks cool, btw." is totally fair.
Assuming bad intent, malware, or hidden wrongdoing is not neutral criticism - it is warrantless attack.
No-one knows who you are, and you’re clearly not against using something like GH Actions in a way other than its intended purpose. What’s to say you won’t pivot to running a tiny VM on my machine and making it available to others?
Is that right? Well, some people know. I’m Cris, and you are?
But wait I’ve been building so much, for all this time, but you think what I’ve really being doing is building malware, and there’ve been no consequences, somehow nobody’s noticed and I’ve just “gotten away with it”?
I don’t think anything, and I’m not accusing you of anything, I’m just saying, a lot of folks started with pure motives and got poisoned along the way.
For what it’s worth, it’s not very reassuring that you have a bunch of open source projects but you’ve decided this one is not going to be. Rather than showing I can trust you, it rather makes me wonder what you’re hiding.
The answer may well be nothing, but it’s still strange.
I get you might feel that way about it, but that’s not how it is.
The strange thing is your reaction, don’t you think: If you see a proprietary source product and you think “what’s it hiding?” and if you can’t respect a boundary of not revealing source without projecting an imagined bad onto that, that’s just you, my dude, and I’m not responsible how you react at all.
So you might wanna try to put your mistaken attitude on me, but really you need to own that. And your attitude seems mistakenly entitled.
Also the trust issues are warrantless. And, in reality, if you look at my projects, the most important ones are not “open source”.
You judged too quickly, without context, like many here and arrived at conclusions that are just not warranted.
You shouldn’t be arguing with anyone about that because why you came to those doubts or conclusions is something you have to figure out yourself, it’s not something anyone else can help you with.
> I’m just saying, a lot of folks started with pure motives and got poisoned along the way.
That’s not how I see things. That’s not been my experience of the world. I understand if it’s been yours though. Poor you. I guess in that case my advice is just try to keep in mind that not everyone is gonna have the same kind of negative outlook as you and try to be understanding towards them. There’s a lot of good in the world if you open your eyes to it, I hope you find some.
> if you can’t respect a boundary of not revealing source without projecting an imagined bad onto that, that’s just you, my dude, and I’m not responsible how you react at all
I’m responding to the change, as something worth scrutiny. You used to publish open source projects, now this is closed source. Why?
> So you might wanna try to put your mistaken attitude on me, but really you need to own that. And your attitude seems mistakenly entitled
What mistaken attitude, what am I putting on you, and what is my “entitlement”?
> You judged too quickly
> You shouldn’t be arguing
> my advice is
Please stop dressing up your arguments as some kind of metaphysical commentary on my character. I don’t need advice, I didn’t judge you, and I didn’t plan on arguing.
You built something, some people think it’s cool, a lot of people think it’s problematic. You want to keep it closed source, some people find that worrying.
Keep your faux pity for yourself, engage with me in good faith on the merits of the points I’m making, otherwise we’re done here.
You think I owe you source code, is entitled. You project strange onto change, is low empathy. There's no metaphysics, your unwarranted criticism is a reflection of your character. Don't pretend your weird subjective reaction is anything I need to respond to, nor any reflection of me - it's just you.
You have 0 right to attack or accuse me in any way. That you think you do makes you even more entitled and low empahty. Geez....
Their pattern here of immediately going on the offensive to even the smallest amount of inquiry or criticism is totally normal and not at all suspicious.
Maybe they're just having a bad day. Friendly reminder that you don't have to respond to something as soon as you read it, or even at all.
Yeah, I think that's what the program creates in your github account. I see the source to those files embedded in the executable. (I'm not running the executable, but I downloaded the linux one to my mac to take a look inside.)
And abracadabra - it will return. That's just the crowd madness leading folks from this very thread to abuse the flag/report button on GitHub repo to get it auto-disabled.
I trust it will resurrect once GitHub gets around to inspecting.
I've recently started using blip, which works very similarly to airdrop after the initial pairing has happened. The devices do not need to be on the same network etc.
No issues per se, but academic publishing has deep roots in the latex ecosystem. So templates from publishers are often not available in typst, or the publisher insists on a latex formatted file.
Often supervisors/professors etc will also resist using typst because of the cognitive overhead on their already oversubscribed time. Typst has about 40 years of history to overcome and that will take a long time to do.
This isn't strictly true. Multiple studies have shown that coffee reliably acts to increase alertness and can often boost mood.
Alertness isn't the same thing as energy, which is why people who drink a lot of coffee often feel tired but "wired". The brain is alert but energy is low. Abstaining from coffee can "reset" the nervous system to an extent, but alertness and energy is largely determined by insulin levs in the body. So figuring out what works for you with diet is a much better way of getting more stable energy through the day, regardless of caffeine intake.
I almost never use the desktop app, I have maybe 2-3 conversations over the last year that have nothing to do with my job. Opus (and now Fable) genuinely do seem to "understand" what you intend based off what you're explaining a lot better than other models I've tried.
Gemini gets close in some cases, but it falls over in the actual implementation sometimes. I haven't tried Kimi yet but MiMo isn't too shabby either.
reply