AI chatbots unable to accurately summarise news, BBC finds
AI chatbots unable to accurately summarise news, BBC finds
The BBC's head of news and current affairs says the developers of the tools are "playing with fire."
As always, never rely on llms for anything factual. They're only good with things which have a massive acceptance for error, such as entertainment (eg rpgs)
I tried using it to spit ball ideas for my DMing. I was running a campaign set in a real life location known for a specific thing. Even if I told it to not include that thing, it would still shoe horn it in random spots. It quickly became absolutely useless once I didn't need that thing included
Sorry for being vague, I just didn't want to post my home town on here
You can say Space Needle. We get it.
The issue for RPGs is that they have such "small" context windows, and a big point of RPGs is that anything could be important, investigated, or just come up later
Although, similar to how deepseek uses two stages ("how would you solve this problem", then "solve this problem following this train of thought"), you could have an input of recent conversations and a private/unseen "notebook" which is modified/appended to based on recent events, but that would need a whole new model to be done properly which likely wouldn't be profitable short term, although I imagine the same infrastructure could be used for any LLM usage where fine details over a long period are more important than specific wording, including factual things
The problem is that the "train of the thought" is also hallucinations. It might make the model better with more compute but it's diminishing rewards.
Rpg can use the llms because they're not critical. If the llm spews out nonsense you don't like, you just ask to redo, because it's all subjective.
Or at least as an assistant on a field your an expert in. Love using it for boilerplate at work (tech).
Idk guys. I think the headline is misleading. I had an AI chatbot summarize the article and it says AI chatbots are really, really good at summarizing articles. In fact it pinky promised.
Turns out, spitting out words when you don't know what anything means or what "means" means is bad, mmmmkay.
It got journalists who were relevant experts in the subject of the article to rate the quality of answers from the AI assistants.
It found 51% of all AI answers to questions about the news were judged to have significant issues of some form.
Additionally, 19% of AI answers which cited BBC content introduced factual errors, such as incorrect factual statements, numbers and dates.
Introduced factual errors
Yeah that's . . . that's bad. As in, not good. As in - it will never be good. With a lot of work and grinding it might be "okay enough" for some tasks some day. That'll be another 200 Billion please.
that's the core problem though, isn't it. They are just predictive text machines, not understanding what they are saying. Yet we are treating them as if they were some amazing solution to all our problems
Well, "we" arent' but there's a hype machine in operation bigger than anything in history because a few tech bros think they're going to rule the world.
I'll be here begging for a miserable 1 million to invest in some freaking trains and bicycle paths. Thanks.
alternatively: 49% had no significant issues and 81% had no factual errors, it's not perfect but it's cheap quick and easy.
Flip a coin every time you read an article whether you get quick and easy significant issues
It's easy, it's quick, and it's free: pouring river water in your socks.
Fortunately, there are other possible criteria.
Is it worse than the current system of editors making shitty click bait titles?
Surprisingly, yes
What temperature and sampling settings? Which models?
I've noticed that the AI giants seem to be encouraging “AI ignorance,” as they just want you to use their stupid subscription app without questioning it, instead of understanding how the tools works under the hood. They also default to bad, cheap models.
I find my local thinking models (FuseAI, Arcee, or Deepseek 32B 5bpw at the moment) are quite good at summarization at a low temperature, which is not what these UIs default to, and I get to use better sampling algorithms than any of the corporate APis. Same with “affordable” flagship API models (like base Deepseek, not R1). But small Gemini/OpenAI API models are crap, especially with default sampling, and Gemini 2.0 in particular seems to have regressed.
My point is that LLMs as locally hosted tools you understand the mechanics/limitations of are neat, but how corporations present them as magic cloud oracles is like everything wrong with tech enshittification and crypto-bro type hype in one package.
I've found Gemini overwhelmingly terrible at pretty much everything, it responds more like a 7b model running on a home pc or a model from two years ago than a medium commercial model in how it completely ignores what you ask it and just latches on to keywords... It's almost like they've played with their tokenisation or trained it exclusively for providing tech support where it links you to an irrelevant article or something
Gemini 1.5 used to be the best long context model around, by far.
Gemini Flash Thinking from earlier this year was very good for its speed/price, but it regressed a ton.
Gemini 1.5 Pro is literally better than the new 2.0 Pro in some of my tests, especially long-context ones. I dunno what happened there, but yes, they probably overtuned it or something.
Bing/chatgpt is just as bad. It loves to tell you it's doing something and then just ignores you completely.
I don’t think giving the temperature knob to end users is the answer.
Turning it to max for max correctness and low creativity won’t work in an intuitive way.
Sure, turning it down from the balanced middle value will make it more “creative” and unexpected, and this is useful for idea generation, etc. But a knob that goes from “good” to “sort of off the rails, but in a good way” isn’t a great user experience for most people.
Most people understand this stuff as intended to be intelligent. Correct. Etc. Or they At least understand that’s the goal. Once you give them a knob to adjust the “intelligence level,” you’ll have more pushback on these things not meeting their goals. “I clearly had it in factual/correct/intelligent mode. Not creativity mode. I don’t understand why it left out these facts and invented a back story to this small thing mentioned…”
Not everyone is an engineer. Temp is an obtuse thing.
But you do have a point about presenting these as cloud genies that will do spectacular things for you. This is not a great way to be executing this as a product.
I loathe how these things are advertised by Apple, Google and Microsoft.
-
Temperature isn't even "creativity" per say, it's more a band-aid to patch looping and dryness in long responses.
-
Lower temperature is much better with modern sampling algorithms, E.G., MinP, DRY, maybe dynamic temperature like mirostat and such. Ideally, structure output, too. Unfortunately, corporate APIs usually don't offer this.
-
It can be mitigated with finetuning against looping/repetition/slop, but most models are the opposite, massively overtuning on their own output which "inbreeds" the model.
-
And yes, domain specific queries are best. Basically the user needs separate prompt boxes for coding, summaries, creative suggestions and such each with their own tuned settings (and ideally tuned models). You are right, this is a much better idea than offering a temperature knob to the user, but... most UIs don't even do this for some reason?
What I am getting at is this is not a problem companies seem interested in solving.They want to treat the users as idiots without the attention span to even categorize their question.
-
They were actually really vague about the details. The paper itself says they used GPT-4o for ChatGPT, but apparently they didnt even note what versions of the other models were used.
I have been pretty impressed by Gemini 2.0 Flash.
Its slightly worse than the very best on the benchmarks I have seen, but is pretty much instant and incredibly cheap. Maybe a loss leader?
Anyways, which model of the commercial ones do you consider to be good?
benchmarks
Benchmarks are so gamed, even Chatbot Arena is kinda iffy. TBH you have to test them with your prompts yourself.
Honestly I am getting incredible/creative responses from Deepseek R1, the hype is real, though its frequently overloaded. Tencent's API is a bit under-rated. If llama 3.3 70B is smart enough for you, Cerebras API is super fast.
Qwen Max is... not bad? The reasoning models kinda spoiled me, but I think they have more reasoning releases coming.
MiniMax is ok for long context, but I still tend to lean on Gemini for this.
I dunno about Claude these days, as its just so expensive. I haven't touched OpenAI in a long time.
Oh, and sometimes "weird" finetunes you can find on OpenRouter or whatever will serve niches much better than "big" API models.
EDIT:
Locally, I used to hop around, but now I pretty much always run a Qwen 32B finetune. Either coder, Arcee Distill, FuseAI, R1, EVA-Gutenberg, or Openbuddy, usually.
BBC is probably salty the AI is able to insert the word Israel alongside a negative term in the headline
Some examples of inaccuracies found by the BBC included:
Gemini incorrectly said the NHS did not recommend vaping as an aid to quit smoking
ChatGPT and Copilot said Rishi Sunak and Nicola Sturgeon were still in office even after they had left
Perplexity misquoted BBC News in a story about the Middle East, saying Iran initially showed "restraint" and described Israel's actions as "aggressive"
Perplexity misquoted BBC News in a story about the Middle East, saying Iran initially showed “restraint” and described Israel’s actions as “aggressive”
I did not even read up to there but wow BBC really went there openly.
ShockedPikachu.svg
But every techbro on the planet told me it's exactly what LLMs are good at. What the hell!? /s
Not only techbros though. Most of my friends are not into computers but they all think AI is magical and will change the whole world for the better. I always ask "how can a blackbox that throws up random crap and runs on the computers of big companies out of the country would change anything?" They don't know what to say but they still believe something will happen and a program can magically become sentient. Sometimes they can be fucking dumb but I still love them.
But the BBC is increasingly unable to accurately report the news, so this finding is no real surprise.
Why do you say that? I have had no reason to doubt their reporting
Look at their reporting of the Employment Tribunal for the nurse from Five who was sacked for abusing a doctor. They refused to correctly gender the doctor correctly in every article to a point where the lack of any pronoun other than the sacked transphobe referring to her with "him". They also very much paint it like it is Dr Upton on trial and not Ms Peggie.
It's a "how the mighty have fallen" kind of thing. They are well into the click-bait farm mentality now - have been for a while.
It's present on the news sites, but far worse on things where they know they steer opinion and discourse. They used to ensure political parties has coverage inline with their support, but for like 10 years prior to Brexit, they gave Farage and his Jackasses hugely disproportionate coverage - like 20X more than their base. This was at a time when SNP were doing very well and were frequently seen less than the UK independence party. And I don't recall a single instance of it being pointed out that 10 years of poor interactions with Europe may have been at least partially fuelled by Nidge being our MEP and never turning up. Hell we had veto rights and he was on the fisheries commission. All that shit about fisherman was a problem he made.
Current reporting is heavily spun and they definitely aren't the worst in the world, but the are also definitely not the bastion of unbiased news I grew up with.
Until relatively recently you could see the deterioration by flipping to the world service, but that's fallen into line now.
If you have the time to follow independent journalists the problem becomes clearer, if not, look at output from parody news sites - it's telling that Private Eye and Newsthump manage the criticism that the BBC can't seem to get too
Go look at the bylinetimes.com front page, grab a random story and compare coverage with the BBC. One of these is crowd funded reporters and the other a national news site with great funding and legal obligations to report in the public interest.
I don't hate them, they just need to be better.
I just tried it on deepseek it did it fine and gave the source for everything it mentioned as well.
Do you mean you rigorously went through a hundred articles, asking DeepSeek to summarise them and then got relevant experts in the subject of the articles to rate the quality of answers? Could you tell us what percentage of the summaries that were found to introduce errors then? Literally 0?
Or do you mean that you tried having DeepSeek summarise a couple of articles, didn't see anything obviously problematic, and figured it is doing fine? Replacing rigorous research and journalism by humans with a couple of quick AI prompts, which is the core of the issue that the article is getting at. Because if so, please reconsider how you evaluate (or trust others' evaluations of) information tools which might help or help destroy democracy.
I learned that AI chat bots aren't necessarily trustworthy in everything. In fact, if you aren't taking their shit with a grain of salt, you're doing something very wrong.
This is my personal take. As long as you're careful and thoughtful whenever using them, they can be extremely useful.
Could you tell me what you use it for because I legitimately don't understand what I'm supposed to find helpful about the thing.
We all got sent an email at work a couple of weeks back telling everyone that they want ideas for a meeting next month about how we can incorporate AI into the business. I'm heading IT, so I'm supposed to be able to come up with some kind of answer and yet I have nothing. Even putting aside the fact that it probably doesn't work as advertised, I still can't really think of a use for it.
The main problem is it won't be able to operate our ancient and convoluted ticketing system, so it can't actually help.
Everyone I've ever spoken to has said that they use it for DMing or story prompts. All very nice but not really useful.
Treat LLMs like a super knowledgeable, enthusiastic, arrogant, unimaginative intern.
Which is hilarious, because most of the shit out there today seems to be written by them.
News station finds that AI is unable to perform the job of a news station
🤔
BBC finds lol. No, we slresdy knew about that
The owners of LLMs don't care about 'accurate' ... they care about 'fast' and 'summary' ... and especially 'profit' and 'monetization'.
As long as it's quick, delivers instant content and makes money for someone ... no one cares about 'accurate'
That's why I avoid them like the plague. I've even changed almost every platform I'm using to get away from the AI-pocalypse.
I can't stand the corporate double think.
Despite the mountains of evidence that AI is not capable of something even basic as reading an article and telling you what is about it's still apparently going to replace humans. How do they come to that conclusion?
The world won't be destroyed by AI, It will be destroyed by idiot venture capitalist types who reckon that AI is the next big thing. Fire everyone, replace it all with AI; then nothing will work and nobody will be able to buy anything because nobody has a job.
Que global economic collapse.
No better time to get into self hosting!
Funny, I find the BBC unable to accurately convey the news
Dunno why you're being downvoted. If you're wanting a somewhat right-wing, pro-establishment, slightly superficial take on the news, mixed in with lots of "celebrity" frippery, then the BBC have got you covered. Their chairmen have historically been a list of old Tories, but that has never stopped the Tory party of accusing their news of being "left leaning" when it's blatantly not.
Yeah, haha
Perplexity misquoted BBC News in a story about the Middle East, saying Iran initially showed "restraint" and described Israel's actions as "aggressive"
Perplexity did fail to summarize the article, but it did correct it.
Fuckin news!
But AI is the wave of the future! The hot, NEW thing that everyone wants! ** furious jerking off motion **
I recently had one chatbot refuse to answer a couple of questions, and another delete my question after warning me that my question was verging on breaking its rules... never happened before, thought it was interesting.
I'm pretty sure that every user of Apple Intelligence could've told you that. If AI is good at anything, it isn't things that require nuance and factual accuracy.
Neither are my parents