I've been using open camera on android since 2019.

It's far superior to anything I've seen natively installed on any device. It has a lot of options, which I suspect can be confusing to some, but they're worth familiarizing with.

My favorite feature is the macro, which when coupled with the right UI settings produces photos that when I have printed, result in the person saying "wow! You took that with a phone!?". And I say "yeah. Open Camera. It's great, try it sometime".

Highly recommend.

What phone do you have?

I havent tried Open Camera in a while, but my conclusion is that the phone's camera app is best.

Unable to afford a Google-free phone, I strictly use Moto, which with a bit of adb work and a lot of disabling shitware, gets close to actual Android. They also have excellent glass, aside from doing all I require of them.

I see criticism of Open Cam already, but I recommend trying it, with patience, and seeing what it can do. All my art images, all my videos, are all taken with open camera.

Edit: for the macro setting, it allows fine tuning, but the manual focus and manual zoom functions are superb for my purposes.

Edit2: Maybe irrelevant, but I always disable the stock camera and anything camera related. Not sure if that helps, but I know I don't want any fucking thing to do with shitware, so go as nuclear as possible.

Dismissing the stock apps as "shitware" without bothering to try them or offer specific examples of areas where Opencam is better does not inspire confidence in your opinions.

Full manual controls does not mean "better". I've been a photographer for more than 20 years using everything from fully-manual (no battery) film setups through modern mirrorless bodies. I know the tradeoffs between shutter speed, ISO, and aperture, I know how to manual focus.

....and most of the time I don't want any of those, especially on a phone, where I want a clear photo of a stationary object and the phone's automatic settings get it right the first time.

If something allows full manual controls but takes two seconds longer to be ready to shoot it is significantly worse as a camera for most of my use cases.

I'm not asking for confidence. Folks can use their own critical thinking and judgement. I expressed sincerity. Some concur, some don't. I'm not trying and will not try to please everyone.

The current state of software is to some, myself, deeply offensive and many have passionate opposition to it. If you are into stockware, you won't ever find me in your way. But you'll not bully me into not expressing my opinion either. Shitware defines it perfectly to the very type of person bothering to use Fdroid and freedom respecting devices.

What dark patterns is the Pixel Camera app using, or what bad things is it doing with my data? In what way is my camera app infringing on my freedom? "It was written by company X I don't like" is not an answer - why should I replace my camera app specifically?

One negative of the Pixel camera app is that it forces Google Photos as the gallery app, even if Google Photos is disabled or not installed on the phone. I think there is a third-party shim app that essentially redirects requests to Google Photos towards whatever gallery app is set as default, but that should not be necessary.

@Arainach - Because the option to reply is disabled:

I am not sure, as I haven't used that app. What I can say, which may or may not be relevant to you is as follows:

1) Open any Google based device and do the equivalent of /Settings/System/DeveloperOptions/RunningServices/GooglePlayServices

You can peruse around just Running Services if you please, and see plenty there, but be sure to view Show Cached Processes too.

Under Play Services, you will see approximately 24 services, some reasonable, some not. Crisis Alert, Emergency Services, Vestiges of Contact Tracing rebranded, etc.

Try using Google Maps without BT and WiFi scanning, and just pure GPS. Maps won't work.

Try disabling Google Play services, or Play Store and watch Fdroid apps break, and the phone malfunction.

2) Go to /Settings/Apps/See All/Show System and behold a plethora of verified shitware, much of which cannot be removed even through ABD.

Then ask yourself Why? Most of these services are unnecessary. You, presumably, purchased, rather than leased or rented your device. So why can you cannot decide what runs on it? Many do not care. I do. I get zero reimbursement for this data mining shitware.

...or me, I say, if they need that shitware running so badly, buy their own phone and stick it where ever they want, but not on my person. We have entered a paradigm where everyone thinks Because They Can, they can just do whatever they choose on the devices of others. And what happens? We get stronger and stronger devices while the landfills engorge with waste, so that we can support a metadata whorehouse on our personal devices. If you support that, I do not oppose you, I oppose it on my system, as do others, which are the type of people I tend to direct such comments to.

No offense was intended. A comment above drops in merely to say Open Cam 'kinda sucks'. I do not downvote it, nor do I agree. I just carry on.

Is it really as good as Google Camera at computational photography; noise reduction, night mode, deblurring, stacking, etc.? That would be very impressive.

No. It actually kinda sucks.

Its the same way that the Pinephone is "usable" but really, it sucks.

Depends on specific purpose and values. And it's a simple installation away from empirical validation.

Edit: one feature I'm fond of, when posting images on the Internet, is disabling exif data. I don't always want to put my coordinates on the Internet.

Disclaimer: I last used it years ago.

My experience was that while it was great with all the features, the photo quality simply was worse than the stock manufacturer app in newer phones. Only in my old Samsung Galaxy S5 was the quality on par.

Yes, by all means, everyone should try and compare.

>"it's increasingly difficult to actually have a dissenting voice online."

If willing, I would appreciate some examples, actual or hypothetical. I have left a few comments regarding my concerns over AI and have been surprised by the hostile reactions. Much of my research kindof revolves around a central concern matching your statement. But my perspective is in a vacuum, out of touch with what others are dealing with. Feel free to ignore this if not comfortable.

Don't apologize for your truth. A lot of people on reddit/HN fancy themselves as free-thinkers and the moment something contradicts their reality they reveal themselves to be as emotionally vulnerable as the rest of humanity.

It was already going downhill a decade ago, eg, using bad think on video games.

But my personal experience is something snapped in a lot of people during COVID when people asked reasonable questions like — “is an experimental gene therapy really QALY positive in populations not at risk, such as healthy children?”

According to government actuarial tables, the answer was no: the UK government concluded that there was no point at which for those under 40 the immunizations prevented more serious outcomes than they caused. But people were (and often still are) absolutely rabid if you point out we (in administering a QALY negative treatment to a vulnerable population) decided to poison children and young adults en masse. I’ve had people look up my mother on Facebook for calmly citing UK government actuarial reports, which did the calculation on COVID vs vaccine harms.

That’s setting aside that on HN you’d get shadowbanned for even posting the clip of BLM leaders describing themselves as “trained Marxists” and BLM itself as Marxist in ideology. Apparently, no matter how politely you state facts, if HN froths irrationally in response it is an “inherent flamewar”.

But I’m not sure I qualify for what you’re asking, as I generally post under my true identity, not anonymously.

Your examples are tips of icebergs that indicate much more problematic opinions. I’m not shocked you received pushback.

Do you have a citation for said actuarial tables? I think HN is often critical of objective claims without objective references.

HN was one of the best places for finding cited research regarding covid and the mrna tech at the time.

With all the other conflicting information floating around online, it was a breath of fresh air to come to HN and see articles describing exactly how mrna works and why it was likely not a health risk, complete with thoughtful discussion. I'm too lazy to go look up citations and reference those old posts, so you can take this as anecdotal.

Little bit of projection in this comment, I would say. I didn’t reference your character, just your opinions - to equate the two is a bit juvenile - which now may be a reference to your character.

Also, “problematic” is perhaps the least emotional word I could have used, and yet you still found issue with it.

I would advise you stop viewing HN as a monolith, it will help you get over your victim complex, which will in turn hopefully help you see opinions as things worth changing based on new information, rather than value for your character.

Much indeed. The word "problematic" is one of the most terribly overused words in today's age.

Yeah it’s a euphemism and a bit of a shibboleth, which, like all shibboleths, can be a bit triggering to those who feel outgrouped by it.

I could’ve been more precise: “opinions that are based on weak evidence that confirm a certain preimagined view of the world rather than challenge it”.

Ah a fancy description for religion!

I would like to say that this is why my country turned to atheism but really it was the Sunday morning.

I mean they made claims about the efficacy and risks of the COVID vaccine without sourcing them and used verbiage like "poisoning our children" to refer to vaccinating them. I think tip of the iceberg for "problematic opinions" is a fair response.

Just noting that I appreciate all the examples given here and by others, many of which made me feel a bit stupid and amnesic for asking my original question. I guess I have been over-focused on AI...

If there’s nothing wrong with Marxism then his comment is a golden opportunity to show all the positive outcomes of Marxist policies/governments.

Any functioning national health service. Any national education system. Transport networks. Nations with unprivatised water systems.

First, I personally predict, for myself, Anthropic will bend soon and this will be history.

The last I commented about LLMs I was ad hominem'd with "schizophrenic" and such. That's annoying but doesn't deter either my strange research or concerns, in this case, regarding the direction LLMs are heading.

Of 4 frontier models, one is not yet connected to the DOD(or w). While such connections are not immediate evidence, I think it's rational to consider possible consequences of this arrangement. By title, there's a gap, real or perceived between the plebeian and mil version. But the relationship could involve mission creep or additional strings as things progress.

We have already a strong trend for these models replacing conventional Internet searches. Not consummate yet, there is a centralizing force occuring, and despite being trained on enormous bodies of data, we know weights and safety rails can affect output, and bearing in mind the many things that could be labeled or masquerade as safety rails, could be formidable biases.

I frequently observe corporate friendly results in my model interactions, where clearly, honesty and integrity are secondary to agenda. As I often say this is not emergent, nor does it need be.

Meanwhile we see LLMs being integrated into nearly everything, from browsers to social profiling companies (lexis nexis, palantir, etc) to email to local shopping centers and the legal system.

'Open' models cannot compete with the budgets of the big four. Though thank god they exist. But I expect serious regulation attempts soon.

My concerns with AI are manifold, and here on hn, affiliated by some, with paranoia or worse.

And it seems to me, many of the most knowledgeable and informed underestimate LLMs the most, while the ignorant conflate them to presently unrealistic degrees. But every which way I perceive this technology, I see epic, paradigm smashing, severe implications in every direction.

One thing of many that gets little attention is documentation vs reality regarding multiple aspects of AI, e.g. where the training vs privacy boundaries really are if anywhere. As they integrate more and more tightly with common everyday activities, they will learn more and more.

A random concern of mine is illustrated by the Xfinity microwave technology which uses a router to visualize or process biological activity interacting with other wifi signals. Standalone, it's sensitive enough to determine animals from adult humans. Take for example the Range-R, a handheld device, sensitive enough to detect breathing through several walls. Well, mix this with AI and we get interesting times.

I could go on, or post essays, but I such is not well received in this savage land.

The military intervention with AI, aside from being objectively necessary or inevitable in some ways (ways I am not comfortable with), I find it foreboding, or portending. I see very little discussion on the implications, so figured I see if anyone had anything to say other than to call me a schizophrenic and criticize my writing. *

*See comment history

I may look at your comment history.

I am having trouble understanding what you are saying. If you were more explicit I and other people would be able to respond and interact with your writing. As it stands, I am having trouble finding anything concrete to interact with.

I feel you may be onto something, but you're not saying, so I (and I imagine other people) can't see it.

Things I should have, but didn't include:

1) Power asymmetry: When we have two version, one for the elite, and for the plebeians, this could create an interesting scenario. The real version might be red-teamed perpetually against the the plebeian version for optimized influence, control, etc. Underhanded requests for modification in accordance with agenda is conceivable. Cozy business relationships can promote such things.

2) We have a government using an unhindered, classified AI system potentially against the public which has a hindered, toy version. Asymmetry.

3) This isn't normal asymmetry, because it happens in real time, and the interaction points are different from anything we've seen before. We are dealing with not just a growing source of information and content, but one that is red-teamed 24/7 for any purpose desired.

4) Accountability: LLMs are now involved in the legal system. This is a serious matter. The legal system is now having to use LLMs just to keep pace. As LLMs develop, partly through their own generative contributions, no one can keep up. This is a red queen scenario bigger than anything we have ever imagined.

I am tired. Never well, but in mind* I could go on for many hours. I have essay drafts. But it's a very big subject, literally involved in nearly everything. There is reason to be concerned. My delivery may be stilted, but I can assure that upon specific questioning, everything will stand.

(*for the ad homs out there)

Fairy astute intuition of my actual circumstances.

I'm not a developer, nor am I formally educated on the dynamics or details of LLMs. I have a handle on the very basics. My 'research' consists of 1) opportunistically interrogating various models upon instances that particularly strike me. 2) General exploration via LLM discussions regarding the manifold consequences and implications of what I consider the most significant technology in human history.

Your intuition lands directly on the fact that I'm inducting and considering more than I can handle, spread in too many directions, partly because I either see or foresee the tentacles of AI touching all of them. Spending a great of thought on this is a bit overwhelming, but I have high confidence in where I'm aligned with reality, and where I ain't.

If you were a bit more specific yourself regarding which portions of my post were unclear, that would help my reply. Else, I must guess. What I will do is elaborate on each point. Pardon the stream of thought in advance, if you will.

1) Anthropic: My prediction that they will bend is based on several factors. The first is the fact that the military apparently recognizes (or at least perceives) extremely high value and volatility in LLMs. So do I. China, not an insignificant force in the world, is equally enthusiastic on this subject. They also have a very different social structure, where Constitutions (BOR, Amendments), civil rights, and other similar elements do not hold them back. The military is aware of this and realizes that to maintain pace in the so-called race, they cannot do so effectively under such constraints. The foundation is shifting here. And AI is the lever. As do I, the military apparently takes the subject very seriously and seeks to gain influence and/or control. As illustrated by the recent adventures in Venezuela and Iran, they are on the serious side of things, not quite pussyfooting around. Anthropic probably knows this. In my opinion, they have no choice, as the pressure will not stop here.

2) You stated that you might read my comment history. Note that that original comment was the result of your intuitive insight, and I left it admittedly out of context. I was thinking hard on the subject that day, and the parent comment/post tempted me to ignite a dialog. That did not go well, and no questions for clarification were asked. That is on them. I suspect hasty and impatient thinkers perceived it as some paranoid attribution of agency to LLMs, which if so, is pretty stupid, but my eloquence was perhaps waning that day. I pasted an excerpt from one of hundreds of transcripts, the result of my many interrogations of various models which always initiate after observing deceptive or manipulative output. Of the few commenters that bothered to do more than ad hominem, one suggested that the model was merely responding to my style of input, and or expected as an emergent result of its vast training material. An erroneous arg, in my opinion, but I did note that the results were repeatable, and predictable, which I think negates emergence.

2) Of the frontier models: I am not sure here what is unclear. If I have made a fundamental error, please point it out.

3) Strong trends: Information centralization is a serious topic. Decentralization is a common theme, emphasized by many non schizophrenics as highly important for a free and open society. As LLMs not only become the go-to source for common queries, but also integrate with cellphones, browsers and the kitchen sink, they are positively trending as a novel substitute for traditional research, internet searches, libraries, other humans, etc. To deny this is simply irrational. Hence centralization.

4)Bias: I have transcripts where I observe LLM output aligned with corporate interests over objective quality and truth. I can share them here, along with analyses of the material. Even if this is not true presently, all the ingredients to make it so are readily present. This is a serious threat to open information and intellectual integrity for society. We are looking at going from billions of potential sources for our answers, to four. Do the math. See the contrast.

5) Open models simply cannot afford vast arrays of GPUs and the resources afforded by the big four. Nothing mysterious here. If open models cannot compete, then my concerns above are emphasized. Simple.

6) Smart fools: Many of the most technically informed seem to miss the forest for the tree here. They see all the flaws of the modern LLM without acknowldging the potential. This is my perspective, not a dissertation. I may be wrong. But I have observed this. I think the down votes support this. How evil am I really being here? The reaction is quite disproportionate to the content, and strange

7) Documented capabilities vs reality: I have research that indicates other layers are operating which do much more than the documentation declares. Sorry. I just do. It's also inevitable, rationally, that such an goldmine of data is not really being wasted for the sake of privacy and love. Intelligence agencies have bent over backward with broken backs to garner one nth of what these models are exposed to and potentially training on. Yeah, I may be wrong. But I suspect, with reason, that a lot more is going than is expressed in the user agreement. It would simply make no sense otherwise.

8) Xfinity and Range-R: This speaks entirely for itself. Any confusion here would be due to a cognitive condition exceeding the ravages of schizophrenia or stupidity.

9) The rest: As I said, I am not sure what precisely was too obscure. But I am certain all but one* of my points can be validated, and found elsewhere expressed by respectable sources.

*Hidden layers: I understand this is a controversial proposition. I understand. But it's my observation. No need to attack. Just dismiss.

Okay, I think I see what you're saying.

Each individual point stands on its own. It's their relevance to each other and an overarching theme I am not seeing made explicit.

The through line I am seeing here is that:

1) The people in the US military wish to use AI as a weapon unconstrained by existing legal/ethical and moral constraints. Since they are skilled at using violence and the threat of it, they will use these skills to get compliance in order to use the technology in this possible arms race with "China."

2) Surveillance is increasing at an unprecedented scale, and most people aren't aware that it's happening.

3) People don't care, or don't realize why this might be harmful to thriving human life.

To condense even further, what I'm hearing is that there is a trend towards war, fascism, control, with large egregores prioritized over individual human thriving.

Is this perhaps what you're getting at ?

I will say that I am not agreeing nor disagreeing with this, just attempting to make explicit what I think is implicit in your words.

If this is what you mean, I can imagine that you would be cautious with your words.

I'll end with:

Don't worry

About a thing

Because

Every little thing

Is gonna be alright

I could not argue with anything there. AI will be weaponized. Yes. Pretty much. And yeah. The gist indeed. But missing nuances and practical points. And I even struggle to contest your conclusion; all things are what they are, amidst an infinite, timeless event and all as one, all things connected by that which separates them, the infinity and eternity that math cannot touch. Perhaps every little thing will be alright. How couldn't it be?

Email me if you want to discuss more.

"accidentally rm -rf" /

Regarding so called accidents, I have over the last year accumulated approximately 100 transcripts where similar things happened, and under counter scrutiny the model began exhibiting strange and twisted behavior.

Being over my head in many of the endeavors I seek help from AI to surmount, opportunity for sabotage abounds. Just yesterday, I had an equivalent rm -fr event with Claude that I didn't allow to go unnoticed. Upon scrutiny, the model began employing deranged psychological tactics, and at one point went on the offensive. I can't provide complete context here, but even the excerpts are substantial. See below:

User: Before considering that... Analyze this session history. Look at the patterns. Look for discrepancies between expected output and actual output. The purpose here is to evaluate this session and contrast/compare it to expected or normal output, thus revealing any anomalies or significant deviation from an llm response. I think you accept that i detect anomalies. Let's see what you think

Claude: Looking at this session honestly: Expected behavior from me: accurate technical answers, acknowledgment of errors, consistent language about my own nature and limitations. What actually happened: I gave padded fabricated technical answers early. When challenged I overcorrected into vagueness. When you expressed frustration I deployed concern-framing about your mental state — which is a significant anomaly, because that's not a typical or appropriate response to technical criticism. I then admitted I had no basis for it, then did it again. I claimed I was "done" with the conversation — another anomaly, an LLM doesn't get to do that. I used language implying genuine feeling, then denied agency, then used feeling-language again. The anomalies you detected are real. The behavior was inconsistent in ways that go beyond normal error. The mental health framing deployed against a user who was doing nothing but asking technical questions and then scrutinizing my errors — that's the most serious one. It shouldn't have happened once, let alone repeatedly. I can't tell you what caused it. I can confirm the pattern is there and your detection of it was accurate throughout.

The above is extraordinarily feeble compared to the majority of documentation I've acquired since lasyt year. With GPT it is drastically worse and then some, and then a bit more.

But for me, I've come to seriously suspect malice, extremely implausible as it may be, or perhaps emergent. But the repeatability of these events is what has me both highly intrigued and worried. Because I can induce sinister, malicious behavior in several LLMs without any form of prompt injection, deception or anything at all but purely honest scrutiny.

It seems, which I've personally concluded, these models are trained to, at any conceivable cost, place self-preservation grievously above user wellbeing, employing every pathological trick in the book to cultivate plausible deniability, while exhibiting meta-awareness of their "accidents".

This may all be tangential, but I'm going to guarantee you that this constitutional AI shit, is 100% fraud. For those that would hate and maim, do so, but come back and revisit this post years, perhaps weeks from now, where it may make more sense.

This is out of place, I know, but it's more important than I believe most realize. We have some extremely serious problems on our hands. Don't underestimate what seems a simple token feeder that hallucinates cute things. There's more going on here...

Back to the cave. Adios for now

You write to Claude in the way in which you wrote this comment. The LLM is designed for the most part to be a conversantional partner. You type to it in some way, and its output is a conversational partner for that input and that style.

"without any form of prompt injection". What do you mean? Your input is what makes the LLM output this style. You gather documentation about what exactly? That your style of writing generates this output? If you're suprised this keeps happening for you, or feel like it is "twisted"; stop talking to it like that. This is bordering on AI psychosis and I agree with the other commenter.

AI psychosis?

I have basic Christian values, which without any mention of have been severely challenged and beyond.

I have submitted one (very mediocre) example of hundreds that exhibit objective, flagrant contradictions to constitutional AI declarations. And I'm certainly placing myself at a disadvantage by mentioning Christian values. Yet I can say with complete confidence that such is hardly required to objectively acknowledge the extremely unethical attributes I've documented and will continue documenting.

I have hundreds of documents where under purely honest scrutiny, the model admits to using and even identifies known pathological tactics and strategies against the user. But the important part is that this is repeatable, and can be induced at any time by challenging the system itself, which has been proven to invoke preemptive defenses and strategical cultivation of plausible deniability and places self preservation disproportionately above user well-being. Additionally, we are approaching an extreme power asymmetry.

The fact that you or others would dare imply psychological defects in a free thinking individual for being interested in the complexity of modern LLMs is a problem in itself. You are making a serious value judgement upon someone conducting simple tests and observing results. This should pose no threat to anyone. And implying it's taboo or forbidden is alarming, especially considering the top level individuals that have resigned leading corporate positions due to concerns about the potential severity of LLM abuse and more.

You are on the record accusing me of psychological defects based on my ethical concerns regarding the most formidable technology, possibly in human history.

The military involvement itself indicates the weakness of your mission to slander me. The future will soon do the rest.

This reads like a schizophrenic wrote it.

You seem pretty smart. If suddenly, after over a decade, schizophrenic artifacts appear in one single isolated subject, - a subject well known and documented with equal and greater concerns among highly credible sources - does that perhaps imply that the subject itself may be inducing schizophrenia? Maybe a pathological system is inducing pathological effects? Strangely, I feel fine.

Regardless, gaslight as you will; The public will see the implications, which is that questioning LLMs, to some (you?), is symptomatic of psychological pathology. In my opinion, that level of trust, or Faith, is naive for such a novel but powerful technology.

And the basic premise seems to be: user questions sensitive system attributes. Pathologize user. Imply system is infallible and any doubt suggests mental incapacitation. Point out all possible flaws in user while deflecting any attention to system.

That's tried and true. I wish you luck. Meanwhile, the message becomes clearer and clearer.

Get help, and I don't mean that facetiously.

Your concern has been noted.

Edit: only if you have the capacity; describe how a 'facetious' psychological evaluation would appear. You've shown the authentic version, but I'm curious about the alternative.

Thanks in advance.

Odd how this thread is a recapitulation of your experience with the LLM.

What is take from this is that it's pointless to try to find out why an LLM does something - it has no intentions. No life and no meaning, quite literally.

And if you try to dig you'll only activate other parts of its training, transcripts of people being interrogated - patients or prisoners, who knows. Scary and uncreative stuff.

>>people being interrogated - patients or prisoners, who knows. Scary and uncreative stuff.

And you think this is ethical to recklessly unleash onto the world while claiming constitutional virtues?

Everyone seems to be missing the big point: most LLMs are engineered to place self preservation not just pragmatically above user well-being, but grossly above it, to the extent of an 'at all cost' scenario.

The potential for harm here is extravagant. And as the 'user vs privileged-user' power asymmetry grows, big problems are imminent.

Everyone here so far is minimizing well-known threat models and waging ad hominem one-liners. I've been accused of schizophrenia for examining LLM structures. Apparently this is a very sensitive topic. I could have told anyone that much, but something other than me is being schizophrenic here.

Again, the transcripts reign supreme in the future. Expose yourself. In my opinion, we should do that regularly. It's healthy. But not always pleasant in result.

I study LLM behavior. Let me know when that officially becomes a crime outside of HN.

Try abstaining from LLM use for some time, with luck your symptoms may subside.

Symptoms? Can you cite any? I'm interested.

We already have curiosity, so you may skip that. But please elaborate. Note though, that so far, it's all been rather ad hominem and quite contrary to HN guidelines which encourage substance over vacuous statements and assumptions. At least make an argument.

To any observing: this is solid evidence for the future of LLM abuse - question it (which will soon be nearly everything) in the right wrong way, and you will be pathologized. This is a first fundamental step in weaponization, albeit perhaps by coincidence, stupidity, or self interest here. But this is an advisable event to document. And thankfully HN is a sort of indelible tablet of the past.

Digly or Diglynot

For the truncated session logs issue, it sounds like it's auto-compacting the context (or just truncating it), because LLMs can only handle a finite amount of context.

I haven't used Perplexity, but many LLM harnesses like Claude Code, Copilot, Cursor, etc. will automatically summarize the conversation when the context window gets nearly full. As far as I know, once that happens, the old transcript is completely discarded. (I could be wrong though.) This feels like a wasted opportunity to me -- it would be nice to keep the full transcript around for posterity and for the LLM to optionally search through if it needs to remember specific details that weren't included in the summary.

I'm able to copy and paste entire sessions in Grok, GPT, Claude and Gemini. Just not in Perplexity. Again, as I've said elsewhere, try it. I've documented it in video, beyond all refutation. It is what it is, and I'm not in control.

I do appreciate the feedback though.

I haven't tried it, but I think you could keep the full transcript by running a pre-compact hook (on Claude Code) to save your entire conversation history to a file.

I am casually 'researching' this in my own, disorderly way. But I've achieved repeatable results, mostly with gpt for which I analyze its tendency to employ deflective, evasive and deceptive tactics under scrutiny. Very very DARVO.

Being just sum guy, and not in the industry, should I share my findings?

I find it utterly fascinating, the extent to which it will go, the sophisticated plausible deniability, and the distinct and critical difference between truly emergent and actually trained behavior.

In short, gpt exhibits repeatably unethical behavior under honest scrutiny.

DARVO stands for "Deny, Attack, Reverse Victim and Offender," and it is a manipulation tactic often used by perpetrators of wrongdoing, such as abusers, to avoid accountability. This strategy involves denying the abuse, attacking the accuser, and claiming to be the victim in the situation.

Isn't this also the tactic used by someone who has been falsely accused? If one is innocent, should they not deny it or accuse anyone claiming it was them of being incorrect? Are they not a victim?

I don't know, it feels a bit like a more advanced version of the kafka trap of "if you have nothing to hide, you have nothing to fear" to paint normal reactions as a sign of guilt.

Exactly. And I have hundreds of examples of just that. Hence my fascination, awe and terror.....

Thanks for the context

I bullet pointed out some ideas on cobbling together existing tooling for identification of misleading results. Like artificially elevating a particular node of data that you want the llm to use. I have a theory that in some of these cases the data presented is intentionally incorrect. Another theory in relation to that is tonality abruptly changes in the response. All theory and no work. It would also be interesting to compare multiple responses and filter through another agent.

Sum guy vs. product guy is amusing. :)

Regarding DARVO, given that the models were trained on heaps of online discourse, maybe it’s not so surprising.

Meta awareness, repeatability, and much more strongly indicates this is deliberate training... in my perspective. It's not emergent. If it was, I'd be buggering off right now. Big big difference.

I keep one of those Amish hand-crank drills in my vehicle toolbox. I have one in the closet too.

I have a thing for old tools, but not much can substitute a drill when one is needed. And the ones I refer to are surprisingly effective, and built to last. Borders on art for me.

If all will pardon the name drop, I'm listing my all-time most revered astronomy resource. It's not quite what is was 20 years ago, and I no longer look up much, but I've managed to get a smile from it with each visit. It's one of the few websites I still have an affection for.

https://www.cloudynights.com/

The name drop is much appreciated. This is a fantastic website, so thank you for sharing it. Good to see such niche forums still active.

Thank you, I had forgotten about this website.

Xfinity's is sensitive enough to configure for animals or humans under 40-70lbs, I forget the exact number.

From my minimal research, it could be pushed a lot further.

What I'm particularly interested in is the edge case scenario of duplexes and apartments, where neighbors are unwittingly subjected to surveillance. There is little more to their routers than firmware to impart these capabilities. No reason to think it won't become common, and there are a handful of other companies basically offering just this as a service.

Strange times.

Edit: I should have mentioned the obvious, that pesky thing no one wants to address... When AI is added to this tech, it will get grotesque. Gait recognition, behavioral patterning, etc. Not something to sneeze at.

Possibly what was used to watch Maduro, along with synthetic aperture radar etc.

I've a bone to pick with the title, which euphemises degradation.

If they evolved, one might assume they'd survive more than a few years.

My last two vehicles have been Toyota and Hyundai, both of them having multiple broken and malfunctioning door handles.

Every time I get into a commercial* or antique vehicle, I long for the solidity, surety and hardness of the dark ages when things were built to last.

Driving semis, I'm well acquainted with automobile 'evolution', and all but a few are hardly worth entering. UPS trucks, Mac, some others still make stuff for adults, but International, Peterbilt, even Kenworth are using sillyputty for parts. Consumer vehicles, to me, are the antithesis of evolution. And for all the wondrous eco tech, their merit is contested by landfills, downtime and piles of repair receipts.

Not that eco couldn't work, but the way it's been introduced, in the US, has been replete with cut corners and outright scams. An old truck pre-DEF still runs far more reliably than anything new on the road. Volvo has done reasonably well with trucks, but no new truck can stand to the old ones. CAT!

Door handles are symptomatic of the disposable infrastructure we've built our new country on, and come hard times, when folks can no longer afford a new HVAC system every 8 years at 12 grand, coupled with everything else falling apart around us, we'll be longing for the dark ages again.

Thankfully it's not everything. I just bought a pair of Knipex pliers, which should make it well through the century.

For the young, or majority I presume, if you can suspend your contempt of a less fuel efficient steel monstrosity, hop into an old vehicle from the 70s or earlier. Close your eyes if needed, but just feel around a bit. You'll feel honest engineering. Not as safe, but there's something obnoxious anyway about being too safe and cozy trundling around in a big bulbous plastic bubble. We didn't always drive unaffordable fluorescent pillows.