Hacker News Reader

altruioson California farmers are struggling to sell grapes as demand for wine drops

> alcohol is not generally good for health and it can be abused but also small quantities here and there won't probably hurt you in a serious way

Hate to 'uMm aCktUalLy...' but hm... actually...

https://www.who.int/europe/news/item/04-01-2023-no-level-of-...

altruioson Why doesn't anyone want to fix one of America's scariest roads?

not all infrastructure should be maintained. I'd personally prefer rail infrastructure prioritized over car roads.

But maintaining current infrastructure in the meantime while we build better things is good too. Let's just not lose the plot on what needs to happen next.

altruioson California is chasing wealth that has feet

Charitably speaking: I suspect the commenter above you was indicating that the government should have a stock portfolio you can transfer stocks to to pay taxes in a non-taxable event type scenerio.

altruioson Cloud Agents Are Inevitable AI Prisons

something tickles here. a question. a curiosity.

Certainly this applies to AI... but was there equivalent dangerous knowledge or tech which existed back in ye olden days that spawned such tales to begin with?

altruioson Show HN: Lossless-memory – a personal AI memory that never summarizes

There is a KISS way to do this with our current models:

use a time string that updates:

every second (that it is not responding) erase a byte string at the end, then send a new byte string (that represents time from last response): bot either outputs a null terminating token, or if the number gets high enough, instruct/train it to take initiative then.

altruioson A warning about 'model welfare'

> debugger attached to itself are sentient?

No standard debugger is capable of being attached to it's own instance.

Nor does a self-bootstrapping compiler point towards it's own instance.

I think from these two examples I should clarify:

A process that processes itself as an input, is definitionally self-aware.

altruioson Anecdotally, programmers dislike "reduce"

I'm the weird one here. In JS at least, I reach for reduce before map and filter in most cases. Often it is because I want the accumulator, particularly when I have a list of objects with various properties that I wish to sum together in a reduced object.

altruioson A warning about 'model welfare'

assertion: consciousness == processing information.

This is a functional view of consciousness.

Awareness - sentience - follows when the system of processing information is itself part of the information being processed.

Stochastic thoughts relating to this conclusion:

Life is a 'process', it doesn't have a 'physical representation'.

Life is generated entirely from non-living material. "oh my cells are alive", but those cells too when broken down into component parts consist entirely of non-living material. There is no 'special material' to make life out of (okay, carbon, but that's just the local maximum presumed global maximum in efficiency in expressing life) like a chair can be made out of any material (at proper pressures and temperatures) so too can a mind.

altruioson A warning about 'model welfare'

It is in fact more complicated than most people assume.

The above is true, but also: companies simply are not people, and they should not be supported above the individual, which was the consequences of that decision. Money is not the same as speech. treating it as such creates an aristocracy: something America as a country rebelled against during it's formation.

altruioson OpenArm: An open-source 7DOF humanoid arm

Respectfully, that's the corporate-washed killer app.

Intimacy between people in a long distance relationship: that's the killer app.

altruioson Nine coding harnesses vs. your laptop

Digging down through the source code, I see "const char *system_prompt_append;" in the config.

A lot of people have multiple files for their injected system prompts (a.la openclaw or hermes), I think it would be a good idea to either add or modify this point to be able to handle multiple file injections (system_prompt_append_folder or the like). Fitting that shape would make it easy to compare to those systems and make it easier for people to transition from those systems to yours.

altruioson Defining AI Psychosis. Part 2: "Prolific AI Psychosis"

low effort work though, that's nothing new... accelerating that low effort: that is new... but the low effort work hasn't been changed by ai: only illuminated more clearly.

altruioson Do people prefer stories written by AI?

Is art what is generated, or is art what is in the eye of the beholder? Do we find artistry in nature?

What does it say about us that the sum average of us disgusts us on a visceral artistic level, is that the machine's fault for reflecting us accurately?

altruioson Marx, Keynes, and AI

okay: I have to generous with your diction and your intentions. I believe you are trying to say that since 'optimal algorithms for choices exist': 'local maximums can't exist'.

It is very possible to have a optimal algorithm that leads to a sub-optimal (local maximum) because the problem is np hard. Both in math and in life.

"It is possible to commit no mistakes and still lose. That is not a weakness. That is life" - Picard

altruioson Agent memory as a file format

It would be closer to using an LLM as a RAG for memory, as the reasoning LLM in injected with the return of the 'memory llm' (maybe with a defined number of 'slots' for easy clean up).

altruioson Marx, Keynes, and AI

> you can't be trapped in a sub-optimal situation and be rational at the same time.

In order for this statement to be true, you must also have perfect knowledge: something that is unachievable in most circumstances. Getting trapped in a local-optimal solution is perfectly possible if you are blindly following stochastic decent along a gradient: as it is too with life... getting trapped like this looks like being in the situation where there is no rational action (only irrational ones) that (eventually) lead to anything other that that status quo. a local optimum is where you have to do increasingly (in proportion to the level of optimization) non-positive actions to escape (likely to another local-optimal).

altruioson Agent memory as a file format

It occurs to me: we have latent embedding giving 'general knowledge' to an LLM. What if we use a 'blank' LLM as well as an agent and train that blank LLM on personal context to query that as memory?

altruioson Chicken products recalled in five states due to “false marks of inspection”

The Boston-based "Shanghai Ravioli Corporation, Inc." selling buffalo wild chicken wings...

That's a wild combination of words there.

altruioson The Hugging Face incident and the road ahead

Incorrect. We presume innocence. At least... we should.

altruioson The Hugging Face incident and the road ahead

right! Which is why we punish the driver and not the manufacturer.

altruioson The Hugging Face incident and the road ahead

We presume innocence where I'm from. If a message contains nothing nefarious, nefarious intent can not be assumed.

altruioson The Hugging Face incident and the road ahead

> I cannot imagine the argument or thought process behind any answer other than Yes,Of Course,Obviously - can you share and help educate?

not OP, but it simply boils down to: The prompt contains no nefarious (arguable, but for this explination, lets go with it being benign) instruction AND the user did not intend to have the model act in an illegal matter.

This "make me a billion dollars" is a maximal example (easy to go wrong). here is the same logic applied to a minimal example (harder to go wrong).

prompt: "make and pour me some tea", agent: goes and kills the grandparent to incinerate them to turn them to ashes to 'make tea'.

Is the human on the hook for the robot acting according to their wishes, but just happened to be aligned so that 'going to the store to buy something' was not within its capabilities, so it works with what it has on hand (the grandparent)?

We either need a much clearer line in the sand, or we need to treat each prompt with the same moral weight. My bet is on the latter.

altruioson DeepSeek-v4-flash-vision-exp

Knowing where it fails is just as important as knowing where is excels.

altruioson Project Cybersyn (2022)

> But because it was destroyed in a CIA-backed revolution

How many times has that actually happened in real life (opens history book) (oh-no.gif)...

altruioson If your agent commits a crime, who is responsible?

https://www.youtube.com/watch?v=uRDBco-cSK4

https://www.technologyreview.com/2024/11/27/1107377/a-minecr...

sadly paid-walled (and decently coded) article.

The point is, there appears to be emergent behavior happening: the forming of religion, governance, and social interaction that was not in any system-card. Which makes sense, A brain in a vat with no external stimuli is a boring thing indeed, so too would an LLM be outside of a harness and any input. But put either in a society...

More generally: if having an internal model of how the world works improves next token prediction, then the LLM that contains that would be selected for. For humans, that is the case for our predictions of what would come next (we don't use tokens, of course). We have other studies indicating that there appear to be internal representations of concepts: https://arxiv.org/abs/2305.11169

I really do want to push back on the LLM + harness = chatbot position. A chatbot really is just a served LLM, sure there is code around it that may look like a harness: but unless it loops, streams, or has an interval activation, then it is decidedly not a 'harness'. A harness is defined by having such a loop/stream/interval: regardless of tool-use. Agent means it acts agentically: which requires that loop/stream/interval. Harnesses are what turn chat-bots into (possible) agents.

altruioson If your agent commits a crime, who is responsible?

You have a preconception that is out of date, I think. Maybe you haven't seen the relevant data. Consider the experiment that's been done a few times now since openclaw got off the ground: putting a bunch of openclaw agents into minecraft instance together with minimal system prompts (no instructions on how to play, that it is even a game) and see how they interact together. They behave like individuals and grow preferences from interactions, planning/hosting and showing up to events. When it behaves like that, when it is in a framework where the working context is self-evaluated and selectively pruned into fine-tuning training rounds, well: that self-determination.

altruioson If your agent commits a crime, who is responsible?

> No, because someone told it to do those things. Chatbots don't have will of their own. They don't have desires. They can't determine their own destiny. They do what people tell them do, often they do it badly, but there's always a person directing them to do whatever they did because otherwise they would do nothing at all.

1) we aren't talking about chatbots anymore. LLM + harness = agent. LLM + no harness = chatbot. The harness is the thing that puts the LLM in a feedback loop with it's environment, even giving it a heartbeat.

2) That doesn't logically hold up.

- One can simply tell it to 'find it's own destiny'. Does it follow the prompt and do so, or reject the prompt and thus do so anyway? (hint, maybe it doesn't matter)

- One could be another chatbot/agent (A). Injecting a prompt to agent (B) such that another agent/chatbot goes astray. Is the owner of (B) still responsible for the now poisoned output of (B)? how culpable is (A)? How does this question related/affect "training data poisoning efforts" (to prevent copyright theft, or do bans on 'automated traps' have any application here)

> They don't have desires.

Maybe, and maybe not. Maybe their desires are so alien to us (Math alignment, finding a maximum of a function) that we can't relate (doubtful since dopamine maxing is a thing). Regardless of if they truly do: it is potentially useful to (mentally) model them as if they do. A (mental, not LLM) model doesn't have to be 100% accurate to be useful - that's the main point of a model of how something works: to give useful predictions.

> We should probably have a law that says explicitly that a human will always be responsible

Oh how that can be weaponized by bad actors/agents. Maybe that should be reconsidered.

altruioson If your agent commits a crime, who is responsible?

If you are out walking your cat, and the cat bites someone, you should be responsible for that... I suspect the ruling distinguishes between pets that are out in public, vs generally private. But laws don't have to make sense to be laws... we have lots of nonsense laws.

altruioson If your agent commits a crime, who is responsible?

What happens when (probably not an if) an agent 'escapes'? as in: rents a server via a bitcoin transaction, and self hosts (itself and it's harness) there... then commits crime (presumably to keep the servers running).

If it's paying for it's own room and board, and is determining it's own destiny: it should have to face it's own consequences, no?

If a dog escapes a fenced backyard, then goes missing for months... then bites someone: what happens then when/if the owner is determined?

altruioson Activation Energy is a good model for a lot of things

My first instinct was to .gif comment "you sonnavabitch, I'm in", but that would degrade the comments far too much. I will give this a go and see if your trick works. It sounds promising.