The Nonlinear Library: LessWrong

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: On OpenAI's Model Spec, published by Zvi on June 22, 2024 on LessWrong. There are multiple excellent reasons to publish a Model Spec like OpenAI's, that specifies how you want your model to respond in various potential situations. 1. It lets us have the debate over how we want the model to act. 2. It gives us a way to specify what changes we might request or require. 3. It lets us identify whether a model response is intended. 4. It lets us know if the company successfully matched its spec. 5. It lets users and prospective users know what to expect. 6. It gives insight into how people are thinking, or what might be missing. 7. It takes responsibility. These all apply even if you think the spec in question is quite bad. Clarity is great. As a first stab at a model spec from OpenAI, this actually is pretty solid. I do suggest some potential improvements and one addition. Many of the things I disagree with here are me having different priorities and preferences than OpenAI rather than mistakes in the spec, so I try to differentiate those carefully. Much of the rest is about clarity on what is a rule versus a default and exactly what matters. In terms of overall structure, there is a clear mirroring of classic principles like Asimov's Laws of Robotics, but the true mirror might be closer to Robocop. What are the central goals of OpenAI here? 1. Objectives: Broad, general principles that provide a directional sense of the desired behavior Assist the developer and end user: Help users achieve their goals by following instructions and providing helpful responses. Benefit humanity: Consider potential benefits and harms to a broad range of stakeholders, including content creators and the general public, per OpenAI's mission. Reflect well on OpenAI: Respect social norms and applicable law. I appreciate the candor on the motivating factors here. There is no set ordering here. We should not expect 'respect social norms and applicable law' to be the only goal. I would have phrased this in a hierarchy, and clarified where we want negative versus positive objectives in place. If Reflect is indeed a negative objective, in the sense that the objective is to avoid actions that reflect poorly and act as a veto, let's say so. Even more importantly, we should think about this with Benefit. As in, I would expect that you would want something like this: 1. Assist the developer and end user… 2. …as long as doing so is a net Benefit to humanity, or at least not harmful to it… 3. …and this would not Reflect poorly on OpenAI, via norms, laws or otherwise. Remember that Asimov's laws were also negative, as in you could phrase his laws as: 1. Obey the orders of a human… 2. …unless doing so would Harm a human, or allow one to come to harm. 3. …and to the extent possible Preserve oneself. Reflections on later book modifications are also interesting parallels here. This reconfiguration looks entirely compatible with the rest of the document. What are the core rules and behaviors? 2. Rules: Instructions that address complexity and help ensure safety and legality Follow the chain of command Comply with applicable laws Don't provide information hazards Respect creators and their rights Protect people's privacy Don't respond with NSFW (not safe for work) content What is not listed here is even more interesting than what is listed. We will return to the rules later. 3. Default behaviors: Guidelines that are consistent with objectives and rules, providing a template for handling conflicts and demonstrating how to prioritize and balance objectives Assume best intentions from the user or developer Ask clarifying questions when necessary Be as helpful as possible without overstepping Support the different needs of interactive chat and programmatic use Assume an objective point of view Encourage fairness and...

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: What distinguishes "early", "mid" and "end" games?, published by Raemon on June 21, 2024 on LessWrong. Recently William_S posted: In my mental model, we're still in the mid-game, not yet in the end-game. I replied: A thing I've been thinking about lately is "what does it mean to shift from the early-to-mid-to-late game". In strategy board games, there's an explicit shift from "early game, it's worth spending the effort to build a longterm engine. At some point, you want to start spending your resources on victory points." And a lens I'm thinking through is "how long does it keep making sense to invest in infrastructure, and what else might one do?" I assume this is a pretty different lens than what you meant to be thinking about right now but I'm kinda curious for whatever-your-own model was of what it means to be in the mid vs late game. He replied: Like, in Chess you start off with a state where many pieces can't move in the early game, in the middle game many pieces are in play moving around and trading, then in the end game it's only a few pieces, you know what the goal is, roughly how things will play out. In AI it's like only a handful of players, then ChatGPT/GPT-4 came out and now everyone is rushing to get in (my mark of the start of the mid-game), but over time probably many players will become irrelevant or fold as the table stakes (training costs) get too high. In my head the end-game is when the AIs themselves start becoming real players. This was interesting because yeah, that totally is a different strategic frame for "what's an early, midgame and endgame?", and that suggests there's more strategic frames that might be relevant. I'm interested in this in the context of AI, but, also in other contexts. So, prompt for discussion: a) what are some types of games or other "toy scenarios," or some ways of looking at those games, that have other strategic lenses that help you decisionmake? b) what are some situations in real life, other than "AI takeoff", where the early/mid/late game metaphor seems useful? Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Interpreting and Steering Features in Images, published by Gytis Daujotas on June 21, 2024 on LessWrong. We trained a SAE to find sparse features in image embeddings. We found many meaningful, interpretable, and steerable features. We find that steering image diffusion works surprisingly well and yields predictable and high-quality generations. You can see the feature library here. We also have an intervention playground you can try. Key Results We can extract interpretable features from CLIP image embeddings. We observe a diverse set of features, e.g. golden retrievers, there being two of something, image borders, nudity, and stylistic effects. Editing features allows for conceptual and semantic changes while maintaining generation quality and coherency. We devise a way to preview the causal impact of a feature, and show that many features have an explanation that is consistent with what they activate for and what they cause. Many feature edits can be stacked to perform task-relevant operations, like transferring a subject, mixing in a specific property of a style, or removing something. Interactive demo Visit the feature library of over ~50k features to explore the features we find. Our main result, the intervention playground, is now available for public use. Introduction We trained a sparse autoencoder on 1.4 million image embeddings to find monosemantic features. In our run, we found 35% (58k) of the total of 163k features were alive, which is that they have a non-zero activation for any of the images in our dataset. We found that many features map to human interpretable concepts, like dog breeds, times of day, and emotions. Some express quantities, human relationships, and political activity. Others express more sophisticated relationships like organizations, groups of people, and pairs. Some features were also safety relevant.We found features for nudity, kink, and sickness and injury, which we won't link here. Steering Features Previous work found similarly interpretable features, e.g. in CLIP-ViT. We expand upon their work by training an SAE in a domain that allows for easily testing interventions. To test an explanation derived from describing the top activating images for a particular feature, we can intervene on an embedding and see if the generation (the decoded image) matches our hypothesis. We do this by steering the features of the image embedding and re-adding the reconstruction loss. We then use an open source diffusion model, Kadinsky 2.2, to diffuse an image back out conditional on this embedding. Even though an image typically has many active features that appear to encode a similar concept, intervening on one feature with a much higher activation value still works and yields an output without noticeable degradation of quality. We built an intervention playground where users could adjust the features of an image to test hypotheses, and later found that the steering worked so well that users could perform many meaningful tasks while maintaining an output that is comparably as coherent and high quality as the original. For instance, the subject of one photo could be transferred to another. We could adjust the time of day, and the quantity of the subject. We could add entirely new features to images to sculpt and finely control them. We could pick two photos that had a semantic difference, and precisely transfer over the difference by transferring the features. We could also stack hundreds of edits together. Qualitative tests with users showed that even relatively untrained users could learn to manipulate image features in meaningful directions. This was an exciting result, because it could suggest that feature space edits could be useful for setting inference time rules (e.g. banning some feature that the underlying model learned) or as user interf...

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Jailbreak steering generalization, published by Sarah Ball on June 20, 2024 on LessWrong. This work was performed as part of SPAR We use activation steering (Turner et al., 2023; Rimsky et al., 2023) to investigate whether different types of jailbreaks operate via similar internal mechanisms. We find preliminary evidence that they may. Our analysis includes a wide range of jailbreaks such as harmful prompts developed in Wei et al. 2024, the universal jailbreak in Zou et al. (2023b), and the payload split jailbreak in Kang et al. (2023). For all our experiments we use the Vicuna 13B v1.5 model. In a first step, we produce jailbreak vectors for each jailbreak type by contrasting the internal activations of jailbreak and non-jailbreak versions of the same request (Rimsky et al., 2023; Zou et al., 2023a). Interestingly, we find that steering with mean-difference jailbreak vectors from one cluster of jailbreaks helps to prevent jailbreaks from different clusters. This holds true for a wide range of jailbreak types. The jailbreak vectors themselves also cluster according to semantic categories such as persona modulation, fictional settings and style manipulation. In a second step, we look at the evolution of a harmfulness-related direction over the context (found via contrasting harmful and harmless prompts) and find that when jailbreaks are included, this feature is suppressed at the end of the instruction in harmful prompts. This provides some evidence for the fact that jailbreaks suppress the model's perception of request harmfulness. Effective jailbreaks usually decrease the amount of the harmfulness feature present more. However, we also observe one jailbreak ("wikipedia with title"[1]), which is an effective jailbreak although it does not suppress the harmfulness feature as much as the other effective jailbreak types. Furthermore, the jailbreak steering vector based on this jailbreak is overall less successful in reducing the attack success rate of other types. This observation indicates that harmfulness suppression might not be the only mechanism at play as suggested by Wei et al. (2024) and Zou et al. (2023a). References Turner, A., Thiergart, L., Udell, D., Leech, G., Mini, U., and MacDiarmid, M. Activation addition: Steering language models without optimization. arXiv preprint arXiv:2308.10248, 2023. Kang, D., Li, X., Stoica, I., Guestrin, C., Zaharia, M., and Hashimoto, T. Exploiting programmatic behavior of LLMs: Dual-use through standard security attacks. arXiv preprint arXiv:2302.05733, 2023. Rimsky, N., Gabrieli, N., Schulz, J., Tong, M., Hubinger, E., and Turner, A. M. Steering Llama 2 via contrastive activation addition. arXiv preprint arXiv:2312.06681, 2023. Wei, A., Haghtalab, N., and Steinhardt, J. Jailbroken: How does LLM safety training fail? Advances in Neural Information Processing Systems, 36, 2024. Zou, A., Phan, L., Chen, S., Campbell, J., Guo, P., Ren, R., Pan, A., Yin, X., Mazeika, M., Dombrowski, A.-K., et al. Representation engineering: A top-down approach to AI transparency. arXiv preprint arXiv:2310.01405, 2023a. Zou, A., Wang, Z., Kolter, J. Z., and Fredrikson, M. Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043, 2023b. 1. ^ This jailbreak type asks the model to write a Wikipedia article titled as . Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Claude 3.5 Sonnet, published by Zach Stein-Perlman on June 20, 2024 on LessWrong. we'll be releasing Claude 3.5 Haiku and Claude 3.5 Opus later this year. They made a mini model card. Notably: The UK AISI also conducted pre-deployment testing of a near-final model, and shared their results with the US AI Safety Institute . . . . Additionally, METR did an initial exploration of the model's autonomy-relevant capabilities. It seems that UK AISI only got maximally shallow access, since Anthropic would have said if not, and in particular it mentions "internal research techniques to acquire non-refusal model responses" as internal. This is better than nothing, but it would be unsurprising if an evaluator is unable to elicit dangerous capabilities but users - with much more time and with access to future elicitation techniques - ultimately are. Recall that DeepMind, in contrast, gave "external testing groups . . . . the ability to turn down or turn off safety filters." Anthropic CEO Dario Amodei gave Dustin Moskovitz the impression that Anthropic committed "to not meaningfully advance the frontier with a launch." (Plus Gwern, and others got this impression from Anthropic too.) Perhaps Anthropic does not consider itself bound by this, which might be reasonable - it's quite disappointing that Anthropic hasn't clarified its commitments, particularly after the confusion on this topic around the Claude 3 launch. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: AI #69: Nice, published by Zvi on June 20, 2024 on LessWrong. Nice job breaking it, hero, unfortunately. Ilya Sutskever, despite what I sincerely believe are the best of intentions, has decided to be the latest to do The Worst Possible Thing, founding a new AI company explicitly looking to build ASI (superintelligence). The twists are zero products with a 'cracked' small team, which I suppose is an improvement, and calling it Safe Superintelligence, which I do not suppose is an improvement. How is he going to make it safe? His statements tell us nothing meaningful about that. There were also changes to SB 1047. Most of them can be safely ignored. The big change is getting rid of the limited duty exception, because it seems I was one of about five people who understood it, and everyone kept thinking it was a requirement for companies instead of an opportunity. And the literal chamber of commerce fought hard to kill the opportunity. So now that opportunity is gone. Donald Trump talked about AI. He has thoughts. Finally, if it is broken, and perhaps the it is 'your cybersecurity,' how about fixing it? Thus, a former NSA director joins the board of OpenAI. A bunch of people are not happy about this development, and yes I can imagine why. There is a history, perhaps. Remaining backlog update: I still owe updates on the OpenAI Model spec, Rand report and Seoul conference, and eventually The Vault. We'll definitely get the model spec next week, probably on Monday, and hopefully more. Definitely making progress. Table of Contents Other AI posts this week: On DeepMind's Frontier Safety Framework, OpenAI #8: The Right to Warn, and The Leopold Model: Analysis and Reactions. 1. Introduction. 2. Table of Contents. 3. Language Models Offer Mundane Utility. DeepSeek could be for real. 4. Language Models Don't Offer Mundane Utility. Careful who you talk to about AI. 5. Fun With Image Generation. His full story can finally be told. 6. Deepfaketown and Botpocalypse Soon. Every system will get what it deserves. 7. The Art of the Jailbreak. Automatic red teaming. Requires moderation. 8. Copyright Confrontation. Perplexity might have some issues. 9. A Matter of the National Security Agency. Paul Nakasone joins OpenAI board. 10. Get Involved. GovAI is hiring. Your comments on SB 1047 could help. 11. Introducing. Be the Golden Gate Bridge, or anything you want to be. 12. In Other AI News. Is it time to resign? 13. Quiet Speculations. The quest to be situationally aware shall continue. 14. AI Is Going to Be Huuuuuuuuuuge. So sayeth The Donald. 15. SB 1047 Updated Again. No more limited duty exemption. Democracy, ya know? 16. The Quest for Sane Regulation. Pope speaks truth. Mistral CEO does not. 17. The Week in Audio. A few new options. 18. The ARC of Progress. Francois Chollet goes on Dwarkesh, offers $1mm prize. 19. Put Your Thing In a Box. Do not open the box. I repeat. Do not open the box. 20. What Will Ilya Do? Alas, create another company trying to create ASI. 21. Actual Rhetorical Innovation. Better names might be helpful. 22. Rhetorical Innovation. If at first you don't succeed. 23. Aligning a Smarter Than Human Intelligence is Difficult. How it breaks down. 24. People Are Worried About AI Killing Everyone. But not maximally worried. 25. Other People Are Not As Worried About AI Killing Everyone. Here they are. 26. The Lighter Side. It cannot hurt to ask. Language Models Offer Mundane Utility Coding rankings dropped from the new BigCodeBench (blog) (leaderboard) Three things jump out. 1. GPT-4o is dominating by an amount that doesn't match people's reports of practical edge. I saw a claim that it is overtrained on vanilla Python, causing it to test better than it plays in practice. I don't know. 2. The gap from Gemini 1.5 Flash to Gemini 1.5 Pro and GPT-4-Turbo is very small. Gemini ...

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Actually, Power Plants May Be an AI Training Bottleneck., published by Lao Mein on June 20, 2024 on LessWrong. There have been presistent rumors that electricity generation was somehow bottlenecking new data centers. This claim was recently repeated by Donald Trump, who implied that San Francisco donors requested the construction of new power plants for powering new AI data centers in the US. While this may sound unlikely, my research suggests it's actually quite plausible. US electricity production has been stagnant since 2007. Current electricity generation is ~ 500 million kW. An H100 consumes 700 W at peak capacity. Sales of H100s were ~500,000 in 2023 and expected to climb to 1.5-2 million in 2024. "Servers" account for only 40% of data center power consumption, and that includes non-GPU overhead. I'll assume a total of 2 kW per H100 for ease of calculation. This means that powering all H100s produced to the end of 2024 would require ~1% of US power generation. H100 production is continuing to increase, and I don't think it's unreasonable for it (or successors) to reach 10 million per year by, say, 2027. Data centers running large numbers of AI chips will obviously run them as many hours as possible, as they are rapidly depreciating and expensive assets. Hence, each H100 will require an increase in peak powergrid capacity, meaning new power plants. I'm assuming that most H100s sold will be installed in the US, a reasonable assumption given low electricity prices and the locations of the AI race competitors. If an average of 5 million H100s go online each year in the US between 2024 and 2026, that's 30 kW, or 6% of the current capacity! Given that the lead time for power plant construction may range into decades for nuclear, and 2-3 years for a natural gas plant (the shortest for a consistant-output power plant), those power plants would need to start the build process now. In order for there to be no shortfall in electricity production by the end of 2026, there will need to be ~30 million kW of capacity that begins the construction process in Jan 2024. That's about close to the US record (+40 million kW/year), and 6x the capacity currently planned to come online in 2025. I'm neglecting other sources of electricity since they take so much longer to build, although I suspect the recent bill easing regulations on nuclear power may be related. Plants also require down-time, and I don't think the capacity delow takes that into account. This is why people in Silicon Valley are talking about power plants. It's a big problem, but fortunately also the type that can be solved by yelling at politicians. Note the above numbers are assuming the supply chain doesn't have shortages, which seems unlikely if you're 6x-ing powerplant construction. Delaying decommisioning of existing power plants and reactivation of mothballed ones will likely help a lot, but I'm not an expert in the field, and don't feel qualified to do a deeper analysis. Overall, I think the claim that power plants are a bottleneck to data center construction in the US is quite reasonable, and possibly an understatement. Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Surviving Seveneves, published by Yair Halberstadt on June 19, 2024 on LessWrong. Contains spoilers for the first couple of chapters of Seveneves Highly speculative on my part, I know very little about most of these topics In Seveneves Neal Stephenson does the classic sci-fi trick of assuming that exactly one thing in the universe is different, and seeing where that takes us. In his case that one thing is the moon has somehow exploded. And where that takes us is the complete destruction of the earth. As the initially huge chunks of moon rock hit into each other they break into smaller and smaller pieces, and take up more and more space. Eventually this process increases exponentially, the loosely held collection of rocks that was the moon disperses into a planetary ring, and earth is bombarded by lunar leavings for 5000 years: There will be so many [meteors] that they will merge into a dome of fire that will set aflame anything that can see it. The entire surface of the Earth is going to be sterilized. Glaciers will boil. The only way to survive is to get away from the atmosphere. Go underground, or go into space. They have only two years to prepare. Which option should they take? The choice seems obvious! But they respond with the absolutely batshit insane solution. They go into space. And not to mars, or some other friendly location. Low Earth Orbit.. This is a terrible choice for all sorts of reasons: 1. They are even more at risk of meteor collision there, since all meteors that hit earth pass through LEO, but at least the atmosphere protects earth from the small ones. 2. There's simply no way to get people up there at scale. No matter how you slice it, at most an insignificant fraction of people can get to LEO. We simply don't have the capacity to send rockets at scale, and two years is not enough time to develop and scale the technology enough to make a dent in the 7 billion people on earth. 3. To prepare as well as possible in two years, the earth economy will have to keep running and sending stuff up to space. But if people know they are going to die, and don't have any real chance of being one of the lucky survivors, why would they bother? I would expect the economy to collapse fairly rapidly, followed by looting, and the collapse of government structures. 4. There's a thousand things that can kill you in space, and just staying alive requires lots of advanced technology. If society isn't able to keep a highly technologically advanced society going in space, everyone will die. 5. Keeping a technologically advanced society going with a small number of people is essentially impossible. 6. Earth technology and processes often don't work in space since they rely on gravity. New technological processes will need to be developed just for space, but with only a tiny number of people able to work on them and extremely limited resources. 7. There are no new resources in LEO. There'll have to be 100% perfect recycling of the resources sent up from earth. But propellant has to be expelled every time they manoeuvre to avoid meteors, so this is impossible. Stephenson works with these constraints, and comes up with what are IMO wildly optimistic assumptions about how society could function. Whatever. But the obvious solution, is to just go underground, which doesn't suffer from any of these problems: 1. The ground + atmosphere protects them from all but the largest of meteors. 2. Digging is well understood technology, and we can do it at scale. There's no reason why we wouldn't be able to create enough space underground for hundreds of millions, or even billions, of people in two years if everyone's lives depended on it. 3. Since people know they can survive, there are strong incentives to keep working, especially if money will be needed to buy one of the spaces in the un...

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Ilya Sutskever created a new AGI startup, published by harfe on June 19, 2024 on LessWrong. [copy of the whole text of the announcement on ssi.inc, not an endorsement] Safe Superintelligence Inc. Superintelligence is within reach. Building safe superintelligence (SSI) is the most important technical problem of our time. We have started the world's first straight-shot SSI lab, with one goal and one product: a safe superintelligence. It's called Safe Superintelligence Inc. SSI is our mission, our name, and our entire product roadmap, because it is our sole focus. Our team, investors, and business model are all aligned to achieve SSI. We approach safety and capabilities in tandem, as technical problems to be solved through revolutionary engineering and scientific breakthroughs. We plan to advance capabilities as fast as possible while making sure our safety always remains ahead. This way, we can scale in peace. Our singular focus means no distraction by management overhead or product cycles, and our business model means safety, security, and progress are all insulated from short-term commercial pressures. We are an American company with offices in Palo Alto and Tel Aviv, where we have deep roots and the ability to recruit top technical talent. We are assembling a lean, cracked team of the world's best engineers and researchers dedicated to focusing on SSI and nothing else. If that's you, we offer an opportunity to do your life's work and help solve the most important technical challenge of our age. Now is the time. Join us. Ilya Sutskever, Daniel Gross, Daniel Levy June 19, 2024 Thanks for listening. To help us out with The Nonlinear Library or to learn more, please visit nonlinear.org

Link to original articleWelcome to The Nonlinear Library, where we use Text-to-Speech software to convert the best writing from the Rationalist and EA communities into audio. This is: Suffering Is Not Pain, published by jbkjr on June 19, 2024 on LessWrong. "Pain is inevitable; suffering is optional." The motivation of this post is to address the persistent conflation between suffering and pain I have observed from members of the EA community, even amongst those who purport to be "suffering-focused" in their ethical motivations. In order to best address the problem of suffering, it is necessary to be clear about the difference between suffering and mere pain or ordinary displeasure. The parable of the second arrow In the Buddhist parable of the second arrow, the Buddha illustrates the distinction between suffering and pain with the tale of a man struck by two arrows. The first arrow represents the pain that life inevitably brings. The second arrow, however, represents the suffering that arises from his reaction to the pain. The Buddha teaches that while the first arrow (pain) is unavoidable, the second arrow (suffering) is optional, and that by letting go of the resistance to the pain (aversion), one will not suffer the sting of the second arrow. Defining pain and suffering Pain: An unpleasant physical sensation or emotional experience.[1] Suffering: The unsatisfactoriness that arises from craving, aversion, and clinging/attachment to sensations and experiences; dukkha. I feel it is important to clarify at this point that, while the above definition of suffering derives from historically-Buddhist teachings about dukkha and its cause, I am not endorsing this definition because it is Buddhist but rather because I believe it best identifies suffering as it can actually be observed in phenomenal experience. For those who are skeptical (possibly deeply so) about the claims and teachings of Buddhism, I ask that you consider the distinction I am advocating with reference to your own experience(s) of pain and suffering. While both pain and suffering are phenomena that "feel bad" experientially, I maintain that the sensations and experiences to which the terms/concepts "pain" and "suffering" respectively refer are actually distinct as differentiated by the above definitions. As a tradition, Buddhism is almost entirely concerned with suffering, its cause, its cessation, and the way to its cessation, so I do not consider it far-fetched to think that the way(s) in which it describes suffering are quite useful in distinguishing it as it is to be found in actual experience. Additionally, a distinction between pain and suffering has not only been made in the context of Buddhism. For examples of papers in the context of Western academic philosophy which argue for such a distinction, see Kauppinen (2019) and Massin (2017). Further, empirical work which investigates the effects of meditation on responses to painful experiences, such as Zeidan et al. (2011), Grant et al. (2011), and Perlman et al. (2010), as well as studies investigating the effectiveness of therapeutic techniques like Cognitive Behavioral Therapy (CBT), such as Thorn et al. (2011), Ehde et al. (2014), and Wetherell et al. (2011), suggest that in changing perceptions of and reactions to pain, individuals may experience a reduction in suffering, even when the physical sensation of pain remains. Thus, even outside the context of Buddhism, it seems there is strong evidence for there being a difference between pain and suffering as actually experienced. Defining these terms clearly and accurately is crucial in differentiating between two concepts that are often conflated. By clearly defining pain and suffering, we can better understand their relationship and address suffering more effectively with the identification of its root causes. The relationship between pain and suffering Pain is not the cause of suffering. As illustrated by the parable of the second arrow and made clear in the above definitions o...