Grokipedia
嗯,用户让我总结这篇文章的内容,控制在100字以内,而且不需要用“文章内容总结”之类的开头。直接写描述就行。首先,我需要仔细阅读文章,理解作者的观点和主要论点。 文章的作者是Tim Bray,他在介绍Grokipedia时提到,这个平台生成了超过七千字的个人词条,远超维基百科的1300字。他指出内容由LLM生成,包含大量错误和自我矛盾,并且引用来源不可靠。此外,Grokipedia试图对抗维基百科的“woke”倾向,但内容显得冗长且有偏见。最后,他认为Grokipedia目前实用性不高。 接下来,我需要将这些要点浓缩到100字以内。要确保涵盖主要内容:生成方式、错误、引用问题、政治倾向以及实用性评价。同时保持语言简洁明了。 可能的结构是:先介绍Grokipedia的内容生成方式和问题,然后提到其政治立场和实用性不足。这样既全面又简洁。 现在试着组织语言:“Tim Bray介绍了Grokipedia平台生成的个人词条,指出内容由LLM生成,包含大量错误和自我矛盾,并且引用来源不可靠。该平台试图对抗维基百科的‘woke’倾向,但内容显得冗长且有偏见。Bray认为目前实用性不高。” 检查字数是否在100字以内,并确保没有使用禁止的开头语句。 </think> Tim Bray介绍了Grokipedia平台生成的个人词条,指出内容由LLM生成,包含大量错误和自我矛盾,并且引用来源不可靠。该平台试图对抗维基百科的“woke”倾向,但内容显得冗长且有偏见。Bray认为目前实用性不高。 2025-10-28 19:0:0 Author: www.tbray.org(查看原文) 阅读量:3 收藏

Last night I had a very strange experience: About two thirds of the way through reading a Web page about myself, Tim Bray, I succumbed to boredom and killed the tab. Thus my introduction to Grokipedia. Here are early impressions.

On Bray · My Grokipedia entry has over seven thousand words, compared to a mere 1,300 in my Wikipedia article. It’s pretty clear how it was generated; an LLM, trained on who-knows-what but definitely including that Wikipedia article and this blog, was told to go nuts.

Speaking as a leading but highly biased expert on the subject of T. Bray, here are the key take-aways:

(Overly) complete · It covers all the territory; there is no phase of my life’s activity that could possibly be encountered in combing the Web that is not exhaustively covered. In theory this should be good but in fact, who cares about the details of what I worked on at Sun Microsystems between 2004 and 2010? I suppose I should but, like I said, I couldn’t force myself to plod all the way through it.

Wrong · Every paragraph contains significant errors. Sometimes the text is explicitly self-contradictory on the face of it, sometimes the mistakes are subtle enough that only I would spot them.

Style · The writing has that LLM view-from-nowhere flat-affect semi-academic flavor. I don’t like it but the evidence suggests that some people do?

References · All the references are just URLs and at least some of them entirely fail to support the text. Here’s an example. In discussion of my expert-witness work for the FTC in their litigation against Meta concerning its acquisitions of Instagram and WhatsApp, Grokipedia says:

[Bray] opined that users' perceptions of response times in online services critically influence market dynamics.

It cites Federal Trade Commission’s Reply to Meta Platforms, Inc.’s Response to Federal Trade Commission’s Counterstatement of Material Facts (warning: 2,857-page PDF). Okay, that was one of the things I argued, but the 425 pages of court documents that I filed, and the references to my reporting in the monster document, make it clear that it was one tiny subset of the main argument.

Anyhow, I (so that you won’t have to) spent a solid fifteen minutes spelunking back and forth through that FTC doc, looking for strings like “response time” and “latency” and so on. Maybe somewhere in those pages there’s support for the claim quoted above, but I couldn’t find it.

Useful? · Wikipedia, in my mind, has two main purposes: A quick visit to find out the basics about some city or person or plant or whatever, or a deep-dive to find out what we really know about genetic linkages to autism or Bach’s relationship with Frederick the Great or whatever.

At the moment, Grokipedia doesn’t really serve either purpose very well. But, after all, this is release 0.1, maybe we should give it a chance.

Or, maybe not.

Woke/Anti-Woke · The whole point, one gathers, is to provide an antidote to Wikipedia’s alleged woke bias. So I dug into that. Let’s consider three examples of what I found. First, from that same paragraph about the FTC opinion quoted above:

While Bray and aligned progressives contend that such dominance stifles innovation by enabling predatory acquisitions and reduced rivalry—evidenced by fewer startup exits in concentrated sectors—counterarguments highlight that Big Tech's scale has fueled empirical gains, with these firms investing over $240 billion in U.S. R&D in 2024 (more than a quarter of national totals) and driving AI, cloud, and patent surges.[128] [131] Six tech industries alone accounted for over one-third of U.S. GDP growth from 2012–2021, comprising about 9% of the economy and sustaining 9.3 million jobs amid falling consumer prices and rapid technological diffusion. [132] [133] Right-leaning economists often defend consumer welfare metrics and market self-correction, warning that forced divestitures risk eroding the efficiencies and investment incentives that have propelled sector productivity above 6% annual growth in key areas like durable manufacturing tech. [134] [135]

I’ve linked the numbered citations to the indicated URLs. Maybe visit one or two of them and see what you think? Four are to articles arguing, basically, that monopolies must be OK because the companies accused of it are growing really fast and driving the economy. They seem mostly to be from right-wing think-tanks but I guess that’s what those think-tanks are for. One of them, #131, Big Tech and the US Digital-Military-Industrial Complex, I think isn’t helpful to the argument at all. But still, it’s broadly doing what they advertise: Pushing back against “woke” positions, in this case the position that monopolization is bad.

I looked at a couple of other examples. For example, this is from the header of the Greta Thunberg article:

While credited with elevating youth engagement on environmental issues, Thunberg's promotion of urgent, existential climate threats has drawn scrutiny for diverging from nuanced empirical assessments of climate risks and adaptation capacities, as well as for extending her activism into broader political arenas such as anti-capitalist and geopolitical protests.[5][6]

Somehow I feel no urge to click on those citation links.

If Ms Thunberg is out there on the “woke” end of the spectrum, let’s flit over to the other end, namely the entry for J.D. Vance, on the subject of his book Hillbilly Elegy.

Critics from progressive outlets, including Sarah Smarsh in her 2018 book Heartland, faulted the memoir for overemphasizing personal and cultural failings at the expense of structural economic policies, arguing it perpetuated stereotypes of rural whites as self-sabotaging.[71] These objections, often rooted in institutional analyses from academia and media, overlooked data on behavioral patterns like opioid dependency rates—peaking at 21.5 deaths per 100,000 in Appalachia around 2016—that aligned with Vance's observations of "deaths of despair" precursors.[72]

I read and enjoyed Heartland but the citation is to a New Yorker article that doesn’t mention Smarsh. As for the second sentence… my first reaction as I trudged through its many clauses, was “life’s too short”. But seriously, opioid-death statistics weaken the hypothesis about structural economic issues? Don’t get it.

Take-away · Wikipedia is, to quote myself, the encyclopedia that “anyone who’s willing to provide citations can edit”. Grokipedia is “the encyclopedia that Elon Musk’s LLM can edit, with sketchy citations and no progressive argument left un-attacked.”

So I guess it’s Working As Intended?



文章来源: https://www.tbray.org/ongoing/When/202x/2025/10/28/Grokipedia
如有侵权请联系:admin#unsafe.sh