I am a generalist quantitative researcher. I am open to volunteering and paid work. I welcome suggestions for posts. You can give me feedback here (anonymously or not).
Vasco Grilošø
Karma: 11,636
Hello. Thanks for sharing. Yesterday I created a WhatsApp group for people interested in effective altruism in Porto. It is under the WhatsApp community Effective Altruism and Rationality Portugal, where I just shared the post above.
You may want to add deadlines for submitting the application forms, and consider having a single form for all applications (where people can specify the location they are interested in).
ExĀpandĀing agriĀculĀtural land may inĀcrease or deĀcrease the welfare/āsufferĀing/āhapĀpiness of soil invertebrates
I am very uncertain about whether decreasing the number of farmed animals increases or decreases animal welfare (in expectation) due to potentially dominant effects on soil invertebrates. In addition, I worry decreasing the number of farmed animals may prevent some from having positive lives.
Hi David. Great post. I broadly agree. Relatedly, readers may be interested in the post AI Welfare Is (Frankfurtian) Bullshit.
I sometimes felt you were implying āno evidenceā when I thought something closer to āvery weak evidenceā would be more appropriate. However, in practice, I would agree the focus should overwhelmingly be on decreasing the uncertainty about the extent to which AI models have welfare, and how to measure it.
I donāt find this convincing. (NB: Iām still working on this response.) Even if the talker has no access to the valenced consciousness, itās model may simply lead it to a confident and wrong answer about this.
Did you mean āIfā instead of āEven ifā?
Wha tmight
Nitpick. āWhat mightā.
Hi AĆÆda. That makes sense. However, I think the reasons you mentioned sometimes play against increasing animal welfare. Poorer welfare standards tend to have a lower carbon and land footprint.
Hi Phalox. Thanks for the comment. You may be interested in my post āInsecticide-treated nets [ITNs] significantly harm mosquitoes, but one can easily offset this?ā, where I compared the effects of ITNs on humans and mosquitoes.
Relatedly, saving human lives also affects soil invertebrates due to resulting in more agricultural land to feed the people who are saved, and I think the effects on soil invertebrates may be much larger or smaller than the benefits to humans. I calculate that GiveWellās top charities change the living time of soil invertebrates by 539 M animal-years per $, and that of soil arthropods by 10.8 M animal-years per $. As illustrated in the graph below, I estimate such charities may change the welfare of soil invertebrates much more or less than they they benefit humans. The title of graph says āIncrease in the welfareā, not āChange in the welfareā, because I assumed expanding agricultural land increases the welfare of soil invertebrates, but I am very uncertain about this. The estimates below suppose welfare per fully-healthy-animal-year is proportional to āindividual number of neuronsā^āexponentā. An exponent between 0 and 2 covers the best guesses that I consider reasonable.
Hi Jasmine. I very much agree we should not assume AI welfare will never be measurable. On the other hand, I believe acting as if AIs have welfare makes less sense for greater uncertainty about their welfare, and how to measure it. I think more uncertainty generally implies efforts to decrease it have a greater value of information. I would say uncertainty is currently very large. So I would overwhelmingly focus on decreasing it instead of acting as if AIs have welfare.
Hi Gregory. Great post. Here is a podcast I liked about it which I generated with NotebookLM.
I see. That makes sense. I was thinking you were not interested in consciousness research more broadly.
@nonn? If you initially getting 1 k$ is not enough to motivate you to look into this bet, I would be happy to increase the stakes, potentially up to you initially 10 k$.
Hi Jasmine. Why are you not interested in consciousness research? Because you do not think progress is possible?
Hi Haoyu. Thanks for sharing your thoughts. They seem quite relevant. I am not one of the authors of the paper, but I let the 1st author know about them.
AI Welfare Is (FrankĀfurĀtian) Bullshit
My apologies @Vasco Grilošø I was lazy there and didnāt read the whole article properly. Thanks for pointing out the important areas.
No worries. I could have highlighted them more too. So thanks for asking. I linked to the relevant section in this comment, but I have now linked to it at the top of the post too. āThe article has a section discussing promising ways of assessing sentience (here is some brief context [my comment just above])ā.
Nitpick. I get email notifications of comments on my posts, and replies to my comments even if I am not tagged. I think this is the default setting on the EA Forum. If I am tagged in those cases, I get 2 email notifications, although this does not bother me.
Working memory and operant conditioning donāt carry any weight with me personally, I struggle to connect those with a meaningfully increased chance of pain experience.
I would also give them the least weight among the 4 indicators, but I am not confident they should have negligible weight. I think negligible weight makes more sense for classical/ārespondant conditioning, as SPUDs are capable of this.
In addition, I believe some types of working memory and operant conditioning should have more weight than others. Here is some brief context from the post.
More stringently, it could be that not all operant learning requires sentience [it demonstrably does not require consciousness of the rewards and punishments], but that only some sub-types do. Thus, it could be that Ginsburg and Jablonkaās (37) hypothesis about second-order conditioning [context] is correct: again something not yet known, but amenable to empirical test. If their hypothesis is supported [it may not be], then again there are already some cases demonstrating conditioned responses to secondary reinforcers by fish.
These higher order processes would be most convincing for me than the memory stuff, especially deeper levels of self recognition which I feel like could maybe be tested?
Perhaps a silly question, but I thought the mirror/āparasite mirror test was related to āself recognitionā, but you seem to mention that as something different.
Both the mirror test and āmirror test with biting parasiteā test self-recognition, but the latter offers stronger evidence for sentience. I asked Gemini 3.5 Flash to contrast the 2 tests with respect to this given the articleās description of the āmirror test with biting parasiteā. The answer is below. I think it is good, except that it is overconfident (as it is often the case with LLMs). Words like āprovesā and ādemonstratesā should be replaced with āoffers stronger evidence (relative to the standard mirror test) forā.
The standard mirror test is widely used to check for self-awareness, but it doesnāt tell us if an animal can actually feel things like pleasure or pain.
Mason and Lavery (2022) proposed a modified version to bridge this gap. Here is how the two tasks contrast and why the new one offers stronger evidence for sentience.
The Two Tasks Contrasted
The Standard Mirror Test (Affectively Neutral): An animal is marked with a spot (like a dot of odorless, painless paint) in a place it can only see using a mirror (like its forehead). If the animal looks in the mirror and then grooms, touches, or scrapes its own body where the mark is, it passes. This proves the animal understands that the reflection is āmeā rather than another animal, showing a baseline of physical and visual self-awareness. However, because the mark doesnāt feel like anything, the task is affectively neutralāit doesnāt involve emotions or feelings.
The āMirror Test with a Biting Parasiteā (Affectively Charged): This version introduces feelings. Instead of a neutral dot, the animal is trained to associate different visual marks with physical comfort or discomfort. For example:
The animal is exposed to a black triangle mark that is physically uncomfortable or painful (simulating a biting parasite).
It is also exposed to a white circle mark that causes no discomfort at all.
Finally, the researchers place these marks on the animalās body without any actual pain or discomfort attached, in a spot the animal can see directly or via a mirror. The test checks if the animal reacts with greater urgency, anxiety, or scraping behaviors toward the ānastyā black triangle than the ābenignā white circle, purely based on what it looks like.
Why the Parasite Test Provides Stronger Evidence for Sentience
To understand why the parasite version is stronger, it helps to separate two concepts: awareness and sentience.
Passing the standard mirror test proves awarenessāspecifically, the cognitive ability to map visual reflections to oneās own physical body. But critics argue that a highly complex, non-sentient robot or AI could theoretically pass this test using pure geometry and visual processing, without experiencing any inner feelings.
The biting parasite test targets phenomenal consciousness (P-consciousness) and affective statesāthe actual capacity to subjectively feel pain, fear, or distress.
By showing that an animal doesnāt just recognize a mark, but specifically anticipates and reacts to the remembered emotional and painful quality of that mark, the test demonstrates that the animal experiences the world through a lens of āgoodā and ābadā feelings. It links visual self-recognition directly to an inner emotional state (the desire to avoid pain), providing much sturdier proof that the animal is truly sentient and capable of suffering.
Hi Nick.
What kind of research do you think could decrease uncertainty about their sentience?
The kind of research described in this section of the article. Tasks involving working memory, aspects of operant conditioning, self-report of sensation, or higher order consciousness (like the āmirror test with biting parasiteā, which offers stronger evidence for sentience than the standard mirror test). Below is some context from the article about why these tasks are promising. I bolded the 4 types of tasks.
here we suggest four types of candidate measure that seem particularly promising as indicators of sentience. One concerns working memory, and another, forms of operant conditioning: two types of ability that S.P.U.D. subjects seem not to convincingly have. A third type of candidate measure concerns self report. As we saw in the section Red Herrings: Responses That Do Not Require Sentience, unaware humans, and also monkeys with blindsight, report sensing nothing (thence having no P-consciousness), even when presented with stimuli that elicit other kinds of response ā with the human subjects consistently describing themselves as merely guessing. Finally, higher order cognitive processes such as episodic memory and self-recognition, can yield insights into animal awareness. These have not been studied in S.P.U.D. subjects, and this would likely be impossible, but are arguably reliant on perceptual consciousness. We review each of these below, and also outline how they could be modified to now address questions about sentience: the ethically relevant dimension of P-consciousness at the heart of the fish pain debate. We also suggest how their validity as indicators of sentience could be assessed.
In addition, tasks involving endogenous/āvoluntary attention, like Posnerās spatial cueing task, as discussed in Nieder (2022).
Iām assuming you mean behavioural research?
All of the above tasks look into behaviour. However, passing them would be stronger evidence for sentience than passing tasks that have been passed by SPUDs (spines disconnected from brains, humans in unaware states, decerebrate mammals and birds, or organisms lacking a nervous system like plants and protozoa).
I think this kind of research is helpful to reduce uncertainty but doesnāt necessarily address fundamental questions about how brains work.
Note that research looking for the neural correlates of consciosness (NCCs) in animals relies on studying the behaviour of humans. In particular, to understand which states of the human brain are responsible for consciousness. Nieder (2022) says there is no evidence for the neural correlates of consciousness in animals besides mammals and birds.
Iām just saying that if youāre not a longtermist, you donāt face as much uncertainty about how to achieve good outcomes
Makes sense.
Not sure what youāre asking exactly
You seem to suggest that longterm effects may not be relevant for global health interventions while being relevant for AI safety interventions (or others which are typically referred to as longtermist interventions). I meant to question this. If I thought longterm effects were relevant for AI safety interventions (I do not), I would think they would be relevant for global health interventions too.
I think the other lists have value, but are more more observational heuristics that might explain many micro issues, but not really help you make sense of the world and how things work overall.
I agree.
Hi Elias.
We face a lot of uncertainty about the sign of our impact.
Therefore, we should be very vigilant about our epistemics to make sure that we are not having a negative impact in expectation.
But trying hard deeply distorts our epistemicsāit makes us more prone to motivated reasoning about what weāre doing, and leaves us with less slack to reflect on it.
Great point.
Crucially, this argument applies much more strongly to people working in ālongtermist areasāāwhich other critiques of trying hard generally donāt do. For example, global health EAs whose terminal value is short-term welfare also face uncertainty about the impact of their actionsābut much less (especially about the sign) than people trying to improve the long-term future.
If interventions decreasing the risk of large catastrophes mostly affected the longterm future, why would the same not apply to global health interventions?
Interventions with negligible longterm effects could still decrease welfare due to effects on soil invertebrates?
Hi Matt. Nice initiative.
Do people come away understanding these 200 concepts well?
From the book āScale: The Universal Laws of Growth, Innovation, Sustainability, and the Pace of Life in Organisms, Cities, Economies, and Companiesā by Geoffrey West:
Footnote 13: