Scaling Laws for Neural Language Models · HackerPapers discussions

Scaling Laws for Neural Language Models — mentioned by dannyw

Mon, 26 Oct 2026 08:00:43 GMT

Pretty much. See “Scaling Laws for Neural Language Models”, a must read IMO https://arxiv.org/html/2001.08361v1 Compute, data, and parameter count are the three logarithmic values that correspond to model performance. So if you find ways of improving training efficiency (the simplest conceptually is probably local/global sliding window attention like Gemma; the latest DeepSeek and Kimis have quite fancy ones), you will be able to have more effective compute, and train smarter models while keeping data and param count the same. If you find this fascinating and want to dive more, I encourage…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by yorwba

Sun, 27 Sep 2026 09:32:37 GMT

I was curious what he was responding to. Per https://authorsguild.org/app/uploads/2026/09/Class-Plaintiff... it was "On July 19, 2019, McCandlish wrote in an OpenAI Slack channel: “We’re not sure if we’re going to release the Foresight LM Scaling paper publicly, but if we do we were thinking about removing all mentions of LibGen, since it's a bit of a sketchy data source." The paper may or may not be https://arxiv.org/abs/2001.08361 where they write "we also test on similarly-prepared samples of Books Corpus [ZKZ+15], Common Crawl [Fou], English Wikipedia, and a collection of…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — HN submission

Fri, 25 Sep 2026 03:27:57 GMT

Scaling Laws for Neural Language Models (first "scaling laws" paper from 2020)

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by cute_boi

Tue, 07 Jul 2026 19:03:23 GMT

No need stupid moving texts. CS231n: Convolutional Neural Networks for Visual Recognition - https://cs231n.github.io/ The Unreasonable Effectiveness of Recurrent Neural Networks - https://karpathy.github.io/2015/05/21/rnn-effectiveness/ Understanding LSTM Networks - https://colah.github.io/posts/2015-08-Understanding-LSTMs/ ImageNet Classification with Deep Convolutional Neural Networks - https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436... Deep Residual Learning for Image Recognition - https://arxiv.org/abs/1512.03385 Multi-Scale Context Aggregation by Dilated Convolutions…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by gooob

Tue, 07 Jul 2026 18:54:32 GMT

https://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436... https://papers.nips.cc/paper_files/paper/2012/file/c399862d3... https://arxiv.org/pdf/1512.03385 https://arxiv.org/pdf/1511.07122 https://arxiv.org/pdf/1603.05027 https://arxiv.org/pdf/1409.2329 https://arxiv.org/pdf/1512.02595 https://arxiv.org/pdf/1409.0473 https://arxiv.org/pdf/1506.03134 https://arxiv.org/pdf/1706.03762 https://nlp.seas.harvard.edu/annotated-transformer/ https://arxiv.org/pdf/1410.5401 https://arxiv.org/pdf/1706.01427 https://arxiv.org/pdf/1806.01822…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by an0malous

Sat, 20 Jun 2026 16:18:10 GMT

No, well known in the current multiverse branch where we still occasionally use things like math and scientific analysis instead of people’s vibe checks and pelican SVGs. Here’s the paper from OpenAI where Dario himself was a co-author: https://arxiv.org/pdf/2001.08361 > We have observed consistent scalings of language model log-likelihood loss with non-embedding parameter count N, dataset size D, and optimized training computation Cmin, as encapsulated in Equations (1.5) and (1.6). Conversely, we find very weak dependence on many architectural and optimization hyperparameters. Since scalings…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by sometimelurker

Sat, 16 May 2026 22:36:13 GMT

I think some attentive VCs couldve predicted this. Paper from OAI 2020 about scaling laws: https://arxiv.org/pdf/2001.08361 The idea that you can make a system smarter by just putting in more money is very appealing. The earliest OAI coding model is here (Aug 2021): https://openai.com/blog/openai-codex/

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by allreduce

Thu, 05 Mar 2026 10:29:26 GMT

Better slop. The effect that these systems get better as you scale up [0] is real you know. [0]: https://arxiv.org/pdf/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by hodgehog11

Fri, 13 Feb 2026 07:16:12 GMT

Fine, that's fair. I believe the statement that you made is countered by my claim, which is: Theorem. For any tolerance epsilon > 0, there exists a transformer neural network of sufficient size that follows, up to the factor epsilon, the policy that most optimally achieves arbitrary goals in arbitrary stochastic environments. Proof (sketch). For any stochastic environment with a given goal, there exists a model that maximizes expected return under this goal (not necessarily unique, but it exists). From Solomonoff's convergence theorem (Theorem 3.19 in [1]), Bayes-optimal predictors under the…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by YetAnotherNick

Fri, 08 Aug 2025 22:30:19 GMT

It wasn't a lie, it was a misrepresentation of the total cost. It's not hard to calculate the cost of the training though. It takes 6 * active parameters * tokens flops[1]. To get number of seconds you can divide by Flops/s * MFU, where MFU is around 45% for H100 for large enough models[2]. [1]: https://arxiv.org/abs/2001.08361 [2]: https://github.com/facebookresearch/lingua

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by Ukv

Wed, 05 Mar 2025 11:31:42 GMT

> The new model seems to prove that longstanding rumors of diminishing returns in training unsupervised-learning LLMs were correct and that the so-called "scaling laws" cited by many for years have possibly met their natural end. The commonly-cited scaling laws[0] predict diminishing returns from scale. Fairly uncontroversial for instance that going from 1 GPU to 2 GPUs gives a larger improvement than going from 101 GPUs to 102 GPUs. Same with, say, computer graphics. I feel scaling laws are getting conflated with the theory of an exponential "hard takeoff" of self-improvement (which isn't…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by vonneumannstan

Mon, 27 Jan 2025 17:34:07 GMT

This is the canonical paper. Nothing I've seen seems to indicate the curves are flattening, you can ask "scaling what" but the trend is clear. https://arxiv.org/pdf/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by YetAnotherNick

Sat, 02 Nov 2024 13:16:43 GMT

You require 6 * parameter * token flops[1] to train LLM. Which means (flop/s of H100 * MFU) / (6 * parameter) token per second. Assuming MFU of 40%, it is (1000 * 10^12 * 0.4) / (6 * 10^9) token/sec = 67,000 token/sec. This repo[2] by Meta achieves 48% MFU, or 80k token/second. [1]: https://arxiv.org/pdf/2001.08361 [2]: https://github.com/facebookresearch/lingua

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by Workaccount2

Fri, 11 Oct 2024 14:34:55 GMT

>if your methodology is flawed you aren't gonna get any more significant returns. The problem with this statement is that predictions made about scaling 5 years ago have held true[1]. We keep adding parameters, adding compute, and the models keep getting more capable. The flaws of LLM's from 2024 are not what is relevant. Just like the flaws of LLMs from 2021 were not relevant. What is relevant is the rate of change, and the lack of evidence that things won't continue on this steep incline. Especially if you consider that GPT4 was sort of a preview model that motivated big money to make…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by logicchains

Thu, 26 Sep 2024 19:20:23 GMT

>I think the data will show that it is going to take logarithmic costs in either train-time or inference-time for linear or even sub-linear improvements. The data already shows this, it's a well-established result: https://arxiv.org/abs/2001.08361 . Well, less established for inference-time compute, but OpenAI even said they saw the same thing for inference compute in their release post for o1. But there's still room for at least an order of magnitude speedup with specialised hardware (as opposed to more general-purpose GPUs) and ternary nets.

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by espadrine

Thu, 26 Sep 2024 15:02:49 GMT

> New LLMs don't even rely that much on that aforementioned older architecture Don’t they all indicate being based on the transformer architecture? > not entirely because of transformers but because of the hardware Kaplan et al. 2020[0] (figure 7, §3.2.1) shows that LSTMs, the leading language architecture prior to transformers, scaled worse because they plateau’ed quickly with larger context. [0]: https://arxiv.org/abs/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by is_true

Sat, 18 May 2024 12:26:29 GMT

a backup just in case https://nlp.seas.harvard.edu/annotated-transformer/ https://scottaaronson.blog/?p=762 https://karpathy.github.io/2015/05/21/rnn-effectiveness/ https://colah.github.io/posts/2015-08-Understanding-LSTMs/ https://arxiv.org/pdf/1409.2329.pdf https://www.cs.toronto.edu/~hinton/absps/colt93.pdf https://arxiv.org/pdf/1506.03134.pdf https://proceedings.neurips.cc/paper_files/paper/2012/file/c... https://arxiv.org/pdf/1511.06391.pdf https://arxiv.org/pdf/1811.06965.pdf https://arxiv.org/pdf/1512.03385.pdf https://arxiv.org/pdf/1511.07122.pdf https://arxiv.org/pdf/1704.01212.pdf…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by findingMeaning

Sun, 10 Mar 2024 18:45:40 GMT

> Why? I’m utterly baffled by this. Yes, me too! I am surprised people are unaware of the empirical power-scale law. [1] Currently, Anthropic's new model has proven it by being better than GPT-4 on some tasks. Yet, the old people are saying it is okay. They are saying engineering is not just coding. What they don't seem to grasp is there won't be a necessity for as many engineers. If people are not willing to accept juniors, where will the next generation of seniors come from? No clue about that. Probably, that spot is reserved for the brilliant minds graduating from R1 institutes. What about…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by hiddencost

Thu, 01 Feb 2024 08:48:54 GMT

Number go up. More seriously, it looks like a potential reduction in the cost to train a neural network. You can think of every meaningful step forward in deep learning as a reduction in the cost of training, or an improvement in the ability of the signal to propagate. https://arxiv.org/abs/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by dwaltrip

Fri, 19 Jan 2024 15:10:21 GMT

https://openai.com/research/scaling-laws-for-neural-language... https://arxiv.org/abs/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by duchenne

Fri, 15 Dec 2023 23:56:47 GMT

The most important paper to understand this issue is "Sacling Laws of Neural Language Models" by Open AI in 2020 [1]. Many consider it the most important paper that predicted the high performance of modern LLMs. This paper shows how the loss decreases when you increase the model size, compute, or training dataset size. From the article: > Convergence is inefficient: When working within a fixed compute budget C but without any other restrictions on the model size N or available data D, we attain optimal performance by training very large models and stopping significantly short of convergence.…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by lappa

Thu, 19 Oct 2023 01:56:44 GMT

More data, more parameters, more compute all result in a better model per "Scaling Laws for Neural Language Models" https://browse.arxiv.org/pdf/2001.08361v1.pdf Largeness is a valid goal.

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by swyx

Wed, 06 Sep 2023 18:31:13 GMT

i highlighted this last night which seems to be making the rounds - https://twitter.com/swyx/status/1699369076529971545 Alec's CV (https://www.linkedin.com/in/alecradford/) seems to be: - 2011-2016 BSc Eng from Olin College - 2013+ started a data/AI consultancy as a sophomore that turned into a vague startup/product? - 2015 first paper on GANs coauthored with soumith https://arxiv.org/pdf/1511.06434.pdf%C3 - 2016 first GAN paper under openai email https://proceedings.neurips.cc/paper_files/paper/2016/file/8... - 2017 the generative reviews paper mentioend in the Wired article, with Ilya…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by circuit10

Wed, 16 Aug 2023 12:23:50 GMT

If you want theory there’s this: https://arxiv.org/abs/2001.08361 (I haven’t actually read this but I know roughly what it’s about) It’s saying that so far the abilities of an LLMs have scaled up with its parameter count and training data size. Of course there’s no way to be sure without actually training larger models but I don’t see why the point where it stops would be just after our current best LLMs. Many properties have already emerged from making it bigger so I don’t see why this would be the exception

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by espadrine

Wed, 26 Jul 2023 15:54:39 GMT

There’s a theoretical, but impractical, way: for a given model, each possible set of weight/bias values yields a specific loss value when ran against the full corpus. There’s at least one set of weight values which minimizes it, for which the idealized bit-per-byte entropy can be computed. That can be compared to what OpenAI’s scaling law paper[0] calls the “entropy of natural language”, which they estimate at about 0.57 bits per byte, based on the differing power law for data vs. compute. In my mind, that highlights more the imprecision of the approach than the information-theoretic content…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by ppaattrriicckk

Mon, 22 May 2023 19:15:27 GMT

I love bashing Intel as much as the other person, but looking at the number of tokens LLaMA[1] was trained on (1,400B tokens), the number of parameters of GPT-3[2] vs. the number of tokens it was trained on (175B params vs. 300B), it's not like the announced 1,000B param model is unreasonable. Taking 175/300*1400 yields 816B parameters - which is fairly close to 1,000B. Not outright the most efficient utilization of data, but as others have mentioned, there might still be something left to gain (from not solely optimizing for compute). E.g. look at Figure 9 in [3]. Although the model trained…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by ftxbro

Sat, 15 Apr 2023 03:38:28 GMT

The ones I had in mind were the newer 'Chinchilla' scaling laws (https://arxiv.org/pdf/2203.15556.pdf) vs. the older 'Kaplan' scaling laws (https://arxiv.org/pdf/2001.08361.pdf)

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by blackbear_

Mon, 20 Mar 2023 11:03:57 GMT

This is exactly what happened with large language models: they are quite useless until a certain number of parameters, after which their abilities quickly become impressive (read more here: http://arxiv.org/abs/2001.08361)

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by vishal0123

Thu, 02 Mar 2023 01:00:31 GMT

https://arxiv.org/pdf/2001.08361.pdf. See the C_forward formula approxiamtion.

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by sandGorgon

Sat, 25 Feb 2023 09:40:22 GMT

hey thanks for your reply. umm...so does OpenAI. In fact this is OpenAI discovery from [1]: >Convergence is inefficient: When working within a fixed compute budget C but without any other restric- tions on the model size N or available data D, we attain optimal performance by training very large models and stopping significantly short of convergence (see Figure 3). Maximally compute-efficient training would therefore be far more sample efficient than one might expect based on training small models to convergence, with data requirements growing very slowly as D ∼ C0.27 with training compute.…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by hackinthebochs

Tue, 14 Feb 2023 23:32:30 GMT

>If you took GPT3's architecture and scaled it down to the size and training set of a typical auto-predict, it would produce near identical results. This is almost certainly not true. The number of parameters is an important feature related to the quality of output. If you scaled the architecture down significantly, it would be significantly less capable[1]. But perhaps I misunderstand your point. >Likewise, if we took an auto-predict architecture from 8 years ago, scaled it up to the size of GPT3 and could train it on GPT3's training set, it would produce similar output to GPT3 This is also…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — HN submission

Mon, 06 Feb 2023 23:47:53 GMT

Ask HN: How “real” are AI scaling laws?

My main question is why would scaling lead to intelligent behavior in an AI and how and why would it generate that intelligent behavior? For this explanation I'm assuming that scaling can lead to an AGI and superintelligent behavior, as some AI engineers claim. Using OpenAI's paper for the base: https://arxiv.org/pdf/2001.08361.pdf You basically have 3 things, compute, dataset and parameter size. The parameters as far as I understand are basically universal computation approximators and can execute any function. The data provides the "geometry" which the parameters try to model with functions…

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by EvgeniyZh

Fri, 03 Feb 2023 19:07:27 GMT

J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020. and multiple follow-ups

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by airgapstopgap

Sat, 28 Jan 2023 13:58:50 GMT

They talk specifically of scaling laws investigated in papers like OpenAI's "Scaling Laws for Neural Language Models" (2020)[1] and Deepmind's "An empirical analysis of compute-optimal large language model training" (2022)[2] which showed that, as far as we could see at the time, for any sensibly designed language model nuances of architecture do not matter nearly as much as the sheer scale of the model, amount of compute spent on training it, and volume of training dataset (or, indeed, that they do not matter at all, or even that attempts to add some cleverness via architecture ultimately…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — HN submission

Thu, 30 Jun 2022 02:13:00 GMT

Scaling Laws for Neural Language Models

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by visarga

Mon, 04 Apr 2022 19:46:30 GMT

Scaling Laws for Neural Language Models - https://arxiv.org/abs/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by kmod

Sat, 19 Mar 2022 17:33:44 GMT

There has been some effort to quantify "AI scaling laws": ie how much performance increases as we scale up the resources involved. See section 1.2 of https://arxiv.org/pdf/2001.08361.pdf My main takeaway from that paper is that a 2x increase in training cost improves performance by 5% (100x by 42%). I only skimmed the paper though. To me this says that model scaling will not get us very much farther: we can probably do one more 100x but not two. I talked to someone working on model scaling and they see the same numbers and draw a very different conclusion: my interpretation of their argument…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by sanxiyn

Tue, 12 Oct 2021 12:12:22 GMT

> What's worse, the trend to supersize language models is never justified, either theoretically (ha ha) or empirically in the relevant literature What? That's absurd. Large language models are motivated by empirical scaling law. It is actually better justified than other ML research. Scaling Laws for Neural Language Models: https://arxiv.org/abs/2001.08361

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by criticaltinker

Wed, 18 Aug 2021 03:41:24 GMT

First, congratulations to you and the other authors - this is a very informative and accessible paper with impressive results. > On both datasets, we find that synthesis performance scales log-linearly with model size This "scaling law" observation is starting to become a major trend in NLP [1] and other other modalities such as speech recognition [2] and protein structure/function prediction [3]. Do you have any insight or commentary to offer regarding the next step in improving program synthesis? For example, will techniques to scale up model size continue to be a primary focus (eg as in…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by Inufu

Mon, 22 Feb 2021 21:20:19 GMT

The author keeps referring to the "PSPACE" complexity of chess and Go in the context of AlphaGo; this is incorrect - these games are only PSPACE for arbitrary large board size N, at fixed board size as actually used by humans and current AI they are just constant O(1), complexity class is not relevant for this. The article was also written before the best evidence we currently have for this was published: scaling laws for natural language understanding (https://arxiv.org/abs/2001.08361), performance of RL algorithms with respect to data (eg AlphaGo Elo vs training time), image model…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by jne2356

Mon, 18 Jan 2021 20:05:36 GMT

OpenAI only trained the full sized GPT-3 once. Hyperparameter sweep was conducted on significantly smaller models (see: https://arxiv.org/abs/2001.08361)

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by jne2356

Mon, 18 Jan 2021 16:38:37 GMT

This is not true. The OpenAI team only trained one full-sized GPT-3, and conducted their hyperparameter sweep on significantly smaller models (see: https://arxiv.org/abs/2001.08361). The compute savings from not having to do the hyperparameter sweep are negligible and do not significantly change the feasibility of the project.

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by Reelin

Fri, 04 Sep 2020 07:29:53 GMT

> The way I interpret the lottery ticket hypothesis is that you don't actually need the full sized networks (with their structure and parameters) in order to perform well at some tasks Actually that's not the point. Pruning typically results in networks that still perform well but are harder to train. The idea is to explicitly search for a subnetwork (via pruning) that is easy to train. > Although what I'll give you is that with smaller networks the required sample size is expected to shrink (due to curse of dimensionality). I'm not so sure about that either. From…

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by Reelin

Fri, 04 Sep 2020 06:00:08 GMT

There's actually a paper that attempts to quantify the scaling characteristics of NLP models from early this year. (https://arxiv.org/abs/2001.08361) Even if scaling alone ends up solving everything (I doubt it), I'd still feel that very significant improvements ought to be possible from an algorithmic perspective. (I realize that's largely baseless, but for some reason I just can't escape the feeling that current algorithms leave a huge amount of potential on the table.)

Paper and discussion history. A mention is not an endorsement.

Scaling Laws for Neural Language Models — HN submission

Mon, 24 Feb 2020 06:24:12 GMT

Scaling Laws for Neural Language Models

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Scaling Laws for Neural Language Models — mentioned by gwern

Sat, 25 Jan 2020 19:08:06 GMT

For example, look at OpenAI's latest paper on scaling Transformers "Scaling Laws for Neural Language Models" https://arxiv.org/abs/2001.08361 , Kaplan et al 2020: larger models are better, in the entire range they test up to billion-parameter models, in pretty much every way - they need hardly any additional data, achieve lower losses, they train faster, they can be parallelized better, and they're even more compute-efficient and sample-efficient (!).

Paper and discussion history. A mention is not an endorsement.