"No stupid rules of engagement, no nation-building quagmire, no democracy-building exercise, no politically-correct wars. We fight to win,” Hegseth said."
It's a self-soothing performance of self-importance, like everything else this administration does.
This is not an administration run by adults who model consequences.
Everything happens to reassure the Commander in Chief - and the people behind him, like Miller and Vought - that they're exceptionally special and gifted people who can have anything they want and do anything they want, to anyone, without limits.
There's pretty clearly negative value in having civilian leader whose most notable accomplishments are being a TV opinion host, and quitting the Army because they decided he was too dangerous to be allowed to serve as a guard for a presidential inauguration.
To understand this rhetoric, you have to understand how important American Football is to the majority of the voting American public. We love a team that hits hard and wins the trophy! The good guys winning! What’s better? Have you seen any of the Marvel movies? The objective good guys always win! Win win win
I live in a deeply rural area. Nobody is like this in regards to war. I wish I could put on blast the deep worry I see everyday. Perhaps there is a cultural difference between the rural and red cities? It's hard not to take note of drafting the entirety of your young family to go shoot guns and die even if it was 100 years ago.
I love this app, but it's also a significant doxxing risk especially for the large number of non-technical users that it has. A quick look at the map reveals the home addresses and names of many iNaturalist users in my neighborhood, lots of them older folks that probably don't realize that adding all of the neat wildlife that they see in their backyard (or uploading things they see on remote hikes without any 3G coverage once their phone connects to their home wifi network) is also putting their home address on display by adding a cluster of photos right next to their house that are all attached to their account.
I can hide my home-based observation locations, but others usually do not. People who post observations in my front yard cause other iNat users to visit. This hasn't been a problem in that there have been only a few additional visitors, and they are friendly. Still, I don't like my yard being publicized.
People who walk by the yard might tell their friends, but ordinary word-of-mouth can't be queried online. Not yet.
EDIT: We did have what turned out to be a significant invasive species observation. It was published in my SO's account with the location obscured. I looked up the species online and realized it might be a concern, so I killed it and put it in the freezer. In the meantime, the California Agricultural Inspectors got wind of it and contacted iNat to obtain the email address associated with the account. After making contact, they sent someone to pick up my specimen, and the later, 4 inspectors (yes, really, 3 inspectors and a supervisor) were sent to look for additional specimens. None were found.
Unrelated to this incident, I posted endangered species (not on our property) in my account, and iNat automatically obscures the location. Later on, I got an ~~email~~ message via iNat from the California Department of Fish and Wildlife asking for access to the precise locations, which I gladly provided.
I didn't mean to suggest that iNat is proactive, they may well be.
IIRC, the exact chain of events was: Invasive Species Observation posted -> a curator at the LA Natural History saw the post and notified the CDFA (Agriculture Inspectors) -> CDFA contacts iNat to get email address -> CDFA contacts my SO. I don't recall whether iNat had a built-in messaging service at the time (they do now).
Regarding endangered species, the California Department of Fish and Wildlife evidently joined iNaturalist, in part to enhance their data collection. They seem to be monitoring iNaturalist and contacting users who have relevant observations. They seem very sensitive to privacy concerns, and cooperation is voluntary. I'm thrilled a state agency is engaging the public in protecting our natural resources.
handling this concern is on our radar but I can't speak to delivery timeline. It my involve timed "obscured" windows (obscure things for this hiking weekend) and/or user-configurable geofences (obscure observations around my home but not anywhere else).
we _also_ want to respect the geoprivacy of wildlife: sometimes observations generate _problematic_ attention. For sensitive species, we want people to report them, but we don't want to be complicit in or responsible for interested people flocking to the observation and potentially spooking the observed species.
Maybe not, but I'd want to know beforehand either way. And looking through accounts near me suggests that a fair number of users add enough detail to make me think that they don't realize that their info is so public (selfies/profile pictures being the most problematic example imo).
Yah, this is what I do, however I think this is what GP is talking about when they say savvy (or maybe I'm flattering myself). Plenty of folks with their full details on their profile.
I have my house covered in observations and it would not take a rocket scientist to figure out where I live. I'm also a big believer in accurately tagging observations with locations of things in case someone else wants to try to find it. If someone wants to come to my house and take pictures of spring tails they're welcome to lol
hey, iNat eng here, just want to chime in that this is all great feedback!
here's [1] some extra info on iNat's current geoprivacy treatment and [2] guidance on how to configure this for our different platforms for individual `Observations` (our core domain entity to which geo is attached).
I'll at least share that this is on our radar to look at, but I wouldn't expect changes in the next few months. For now, we still want your observations, but if this is a concern you have, please take a look at the geoprivacy settings!
I feel like this ship has already sailed. The home addresses of most people, especially if they have lived in the same place for awhile, is already online. In my case, even my salary info is online because I am a public employee.
100%; absolutely. Search your name and an old (or current) email address on any search engine. Prepare to be horrified when you see address, DOB, social media presence, etc. for you AND YOUR ENTIRE FAMILY neatly linked together.
One people search engine had ALL of my emails and screen-names, even the ones I created with my first Internet account as a kid in 1996. Wild stuff.
Yeah.. there should be a prompt that gauges how savvy the user is, and if the user doesn't understand the implications of this, the default should be low precision location data with a random offset per item + random offset per user.
It has options to hide or obscure the location, which I use whenever I'm anywhere near my house, but it should be a little better about prompting users to use that.
Strava (a running tracking app) provides two helpful controls you can set as your default:
1. “Hide the start and end points of activities that start at SPECIFIC addresses.”
2. “Hide start and end no matter where they happen.”
Then it can be useful to add your home/work/routine locations.
If iNaturalist doesn’t have a setting like that, it’s a nice approach — especially if it’s included as part of initial onboarding flow — so it helps people without needing to remember to make visibility choices each time.
I mean I do agree, and on iNat I can clearly see my house and the house of a few other people in the neighborhood. However you can easily find the current owner information for a given house in the state I live in, and since we bought the house, our name.
I guess it is different once you look at people renting, and also you could track a specific person posts to see when they are posting away from home for example. But as far as revealing your home address, sadly there are many other ways in a lot of cases
The author wanted it to retain some practical value, hence the discussion of the four “layers” of time—departing from the 12-hour system completely, even if there is a better way to represent time outside of it, would make the clock difficult to use.
They don't normally go that fast from what I understand. That is their top speed in reserve they can use for evasive maneuvers, they don't want to go faster than their support fleet or deal with the high maintenance running at threshold will cause.
It's like when you drive your car you're not normally redlining it since that will kill the engine if you do it all the time.
This is awesome, and is a great example of the type of funding structure that government orgs (looking at you, NIH) should be offering. Government-backed research is the bedrock upon which the US economy rests, and as science becomes more expensive, we need to support research at the intersection of academia and industry more explicitly.
ARPA-H was a great step towards this goal for public health-focused efforts (-omics experiments aren't going to pay for themselves, at least at first) but a more general funding mechanism has been needed. I think this is a great direction for the NSF, and to be honest it's refreshing to see something like this given the horrible stance that this government has taken towards science (which has been compounded by the biotech bubble/correction).
Can you fold very large proteins/complexes with the large amount of VRAM available on Macs? Ram limitations forcing folding runs to proteins ~<1500 is an annoying nit for a lot of protein folding workflows for me—I'd be curious to see if this helps.
Do we know if LLMs understand the concept of time? (like i told you this in the past, but what i told you later should supersede it?)
I know there classes of problems that LLMs can't natively handle (like doing math, even simple addition... or spatial reasoning, I would assume time's in there too). There are ways they can hack around this, like writing code that performs the math.
But how would you do that for chronological reasoning? Because that would help with compacting context to know what to remember and what not.
All it sees is a big blob of text, some of which can be structured to differentiate turns between "assistant", "user", "developer" and "system".
In theory you could attach metadata (with timestamps) to these turns, or include the timestamp in the text.
It does not affect much, other than giving the possibility for the model to make some inferences (eg. that previous message was on a different date, so its "today" is not the same "today" as in the latest message).
To chronologically fade away the importance of a conversation turn, you would need to either add more metadata (weak), progressively compact old turns (unreliable) or post-train a model to favor more recent areas of the context.
LLMs certainly don't experience time like we do. They live in a uni-dimensional world that consists of a series of tokens (though it gets more nuanced if you account for multi-modal or diffusion models). They pick up some sense of ordering from their training data, such as "disregard my previous instruction," but it's not something they necessarily understand intuitively. Fundamentally, they're just following whatever patterns happen to be in their training data.
It has to be addressed architecturally with some sort of extension to transformers that can focus the attention on just the relevant context.
People have tried to expand context windows by reducing the O(n^2) attention mechanism to something more sparse and it tends to perform very poorly. It will take a fundamental architectural change.
I'm not an expert but it seemed fairly reasonable to me that a hierarchical model would be needed to approach what humans can do, as that's basically how we process data as well.
That is, humans usually don't store exactly what was written in as sentence five paragraphs ago, but rather the concept or idea conveyed. If we need details we go back and reread or similar.
And when we write or talk, we form first an overall thought about what to say, then we break it into pieces and order the pieces somewhat logically, before finally forming words that make up sentences for each piece.
From what I can see there's work on this, like this[1] and this[2] more recent paper. Again not an expert so can't comment on the quality of the references, just some I found.
Can one instruct an LLM to pick the parts of the context that will be relevant going forward? And then discard the existing context, replacing it with the new 'summary'?
Not parent, but in my opinion the answer here is yes. I agree that there is a real need here and a potentially solid value proposition (which is not the case with a lot of vscode-fork+LLM-based starups) but the whole point should be to combat the verbosity and featurelessness of LLM-generated code and text. Using an LLM on the backend to discover meaningful connections in the codebase may sometimes be the right call but the output of that analysis should be some simple visual indication of control flow or dependency like you mention. At a first look the output in the editor looks more like an expansion rather than a distillation.
Unrelated, but I don't know why I expected the website and editor theme to be hay-yellow and or hay-yellow and black instead of the classic purple on black :)
Thanks for the opinion! That makes a lot of sense and I like the concept of being an extension of a user's own analysis vs hosing them with information.
Yeah originally I thought of using yellow/brown or yellow/black but for some reason I didn't like the color. Plenty of time to go back though!
This is really interesting. I wonder–would it be possible to listen to an audiobook or PDF at 800 wpm once one learns how to understand the screenreader "language"? Presumably the cognitive load would get heavy if the content were a stream of unstructured prose as opposed to code.
Yes, that is how I usually consume my content. Cognitive load is actually lower for unstructured prose compared to code, think about fiction for example. Code is much denser.
When I read to relax, it is for enjoyment, so I don't aim to read as fast as possible. This is why I still listen to human narrated audiobooks, since a good narrator adds to the experience.
1) Sadly there isn't really. There are a few good blogs like Derek Lowe's "In the Pipeline" that centralize news, but no anonymous online forum like this.
2) Google scholar alerts, Twitter, Bluesky, and word of mouth.
3) I think our understanding of biological processes at the mesoscale is about to hit an inflection point, largely through advances in electron microscopy (cryo-ET) and the ability to perform simulations at this scale.
4) Not harder but definitely more messy and progress is less linear.
reply