the BBC asked ChatGPT, Copilot, Gemini and Perplexity to summarise 100 news stories and rated each answer. […] It found 51% of all AI answers to questions about the news were judged to have significant issues of some form. […] 19% of AI answers which cited BBC content introduced factual errors, such as incorrect factual statements, numbers and dates.
It makes me remember I basically stopped using LLMs for any summarization after this exact thing happened to me. I realized that without reading the text, I wouldn’t be able to know whether the output has all the relevant info or if it has some made-up info.
I have it write for me emails in German. I moved there not too long ago, works wonders to get doctors appointment, car service, etc. I also have it explain the text, so I’m learning the language.
I also use it as an alternative to internet search, which is now terrible. It’s not going to help you to find smg super location specific, but I can ask it to tell me without spoilers smg about a game/movie or list metacritic scores in a table, etc.
It also works great in summarizing long texts.
LLM is a tool, what matters is how you use it. It is stupid, it doesn’t think, it’s mostly hype to call it AI. But it definitely has it’s benefits.
We have one that indexes all the wikis and GDocs and such at my work and it’s incredibly useful for answering questions like “who’s in charge of project 123?” or “what’s the latest update from team XYZ?”
I even asked it to write my weekly update for MY team once and it did a fairly good job. The one thing I thought it had hallucinated turned out to be something I just hadn’t heard yet. So it was literally ahead of me at my own job.
I get really tired of all the automatic hate over stupid bullshit like this OP. These tools have their uses. It’s very popular to shit on them. So congratulations for whatever agreeable comments your post gets. Anyway.
One thing which I find useful is to be able to turn installation/setup instructions into ansible roles and tasks. If you’re unfamiliar, ansible is a tool for automated configuration for large scale server infrastructures.
In my case I only manage two servers but it is useful to parse instructions and convert them to ansible, helping me learn and understand ansible at the same time.
Results are actually quite good even for smaller 14B self-hosted models like the distilled versions of DeepSeek, though I’m sure there are other usable models too.
To assist you in programming (both to execute and learn) I find it helpful too.
I would not rely on it for factual information, but usually it does a decent job at pointing in the right direction. Another use i have is helpint with spell-checking in a foreign language.
Ask it for a second opinion on medical conditions.
Sounds insane but they are leaps and bounds better than blindly Googling and self prescribe every condition there is under the sun when the symptoms only vaguely match.
Once the LLM helps you narrow in on a couple of possible conditions based on the symptoms, then you can dig deeper into those specific ones, learn more about them, and have a slightly more informed conversation with your medical practitioner.
They’re not a replacement for your actual doctor, but they can help you learn and have better discussions with your actual doctor.
We didn’t stop trying to make faster, safer and more fuel efficient cars after Model T, even though it can get us from place A to place B just fine. We didn’t stop pushing for digital access to published content, even though we have physical libraries. Just because something satisfies a use case doesn’t mean we should stop advancing technology.
We also didn’t make the model T suggest replacing the engine when the oil light comes on. Cars, as it happens, aren’t that great at self diagnosis, despite that technology being far simpler and further along than generative models are. I don’t trust the model to tell me what temperature to bake a cake at, I’m sure at hell not going to trust it with medical information. Googling symptoms was risky at best before. It’s a horror show now.
Writing customer/company-wide emails is a good example. “Make this sound better: we’re aware of the outage at Site A, we are working as quick as possible to get things back online”
Dumbing down technical information “word this so a non-technical person can understand: our DHCP scope filled up and there were no more addresses available for Site A, which caused the temporary outage for some users”
Another is feeding it an article and asking for a summary, https://hackingne.ws/ does that for its Bsky posts.
Coding is another good example, “write me a Python script that moves all files in /mydir to /newdir”
Asking for it to summarize a theory or protocol, “explain to me why RIP was replaced with RIPv2, and what problems people have had since with RIPv2”
Make this sound better: we’re aware of the outage at Site A, we are working as quick as possible to get things back online
How does this work in practice? I suspect you’re just going to get an email that takes longer for everyone to read, and doesn’t give any more information (or worse, gives incorrect information). Your prompt seems like what you should be sending in the email.
If the model (or context?) was good enough to actually add useful, accurate information, then maybe that would be different.
I think we’ll get to the point really quickly where a nice concise message like in your prompt will be appreciated more than the bloated, normalised version, which people will find insulting.
Yeah, normally my “Make this sound better” or “summarize this for me” is a longer wall of text that I want to simplify, I was trying to keep my examples short. Talking to non-technical people about a technical issue is not the easiest for me, AI has helped me dumb it down when sending an email, and helps correct my shitty grammar at times.
As for accuracy, you review what it gives you, you don’t just copy and send it without review. Also you will have to tweak some pieces that it gives out where it doesn’t make the most sense, such as if it uses wording you wouldn’t typically use. It is fairly accurate though in my use-cases.
Hallucinations are a thing, so validating what it spits out is definitely needed.
Another example: if you feel your email is too stern or gives the wrong tone, I’ve used it for that as well. “Make this sound more relaxed: well maybe if you didn’t turn off the fucking server we wouldn’t of had this outage!” (Just a silly example)
I think these are actually valid examples, albeit ones that come with a really big caveat; you’re using AI in place of a skill that you really should be learning for yourself. As an autistic IT person, I get the struggle of communicating with non-technical and neurotypical people, especially clients who you have to be extra careful with. But the reality is, you can’t always do all your communication by email. If you always rely on the AI to correct your tone or simplify your language, you’re choosing not to build an essential skill that is every bit as important to doing your job well as it is to know how to correctly configure an ACL on a Cisco managed switch.
That said, I can also see how relying on the AI at first can be a helpful learning tool as you build those skills. There’s certainly an argument that by using tools, but paying attention to the output of those tools, you build those skills for yourself. Learning by example works. I think used in that way, there’s potentially real value there.
Which is kind of the broader story with Gen AI overall. It’s not that it can never be useful; it’s that, at best, it can only ever aspire to “useful.” No one, yet, has demonstrated any ability to make AI “essential” and the idea that we should be investing hundreds of billions of dollars into a technology that is, on its best days, mildly useful, is sheer fucking lunacy.
Noted, I’ll be giving that a proper read after work. Thank you.
Edit to add: Yeah, that pretty much mirrors my own experiences of using AI as a coding aid. Even when I was learning a new language, I found that my comprehension of the material very quickly outstripped whatever ChatGPT could provide. I’d much rather understand what I’m building because I built it myself. A lot of the time, when you use a solution someone else provided you don’t find out until much later how badly that solution held you back because it wasn’t actually the best way to tackle the problem.
The dumbed down text is basically as long as the prompt. Plus you have to double check it to make sure it didn’t have outrage instead of outage just like if you wrote it yourself.
How do you know the answer on why RIP was replaced with RIPv2 is accurate and not just a load of bullshit like putting glue on pizza?
If the amount of time it takes to create the prompt is the same as it would have taken to write the dumbed down text, then the only time you saved was not learning how to write dumbed down text. Plus you need to know what dumbed down text should look like to know if the output is dumbed down but still accurate.
My experience has been very different, I do have to sometimes add to what it summarized though. The Bsky account mentioned is a good example, most of the posts are very well summarized, but every now and then there will be one that isn’t as accurate.
Here’s a bit of code that’s supposed to do stuff. I got this error message. Any ideas what could cause this error and how to fix it? Also, add this new feature to the code.
Works reasonably well as long as you have some idea how to write the code yourself. GPT can do it in a few seconds, debugging it would take like 5-10 minutes, but that’s still faster than my best. Besides, GPT is also fairly fluent in many functions I have never used before. My approach would be clunky and convoluted, while the code generated by GPT is a lot shorter.
If you’re well familiar with the code you’ve working on, GPT code will be convoluted by comparison. If so, you can ask GPT for the rough alpha version, and you can do the debugging and refining in a few minutes.
It can do that just fine, because it has seen enough examples of working code. It can’t directly count correctly, sure, but it can write “i++;”, incrementing a variable by one in a loop and returning the result. The computer running the generated program is going to be doing the counting.
This but actually. Don’t use an LLM to do things LLMs are known to not be good at. As tools various companies would do good to list out specifically what they’re bad at to eliminate requiring background knowledge before even using them, not unlike needing to somehow know that one corner of those old iPhones was an antenna and to not bridge it.
Yup, the problem with that iPhone (4?) wasn’t that it sucked, but that it had limitations. You could just put a case on it and the problem goes away.
LLMs are pretty good at a number of tasks, and they’re also pretty bad at a number of tasks. They’re pretty good at summarizing, but don’t trust the summary to be accurate, just to give you a decent idea of what something is about. They’re pretty good at generating code, just don’t trust the code to be perfect.
You wouldn’t use a chainsaw to build a table, but it’s pretty good at making big things into small things, and cleaning up the details later with a more refined tool is the way to go.
That depends on how you use it. If you need the information from an article, but don’t want to read it, I agree, an LLM is probably the wrong tool. If you have several articles and want go decide which one has the information you need, an LLM is a pretty good option.
if you want to find a few articles out of a few hundred that are about the benefits of nuclear weapons or other controversial topics that have significant literature on them it can be helpful to eliminate 90% that probably aren’t what I’m looking for.
I think there’s a fundamental difference between someone saying “you’re holding your phone wrong, of course you’re not getting a signal” to millions of people and someone saying “LLMs aren’t good at that task you’re asking it to perform, but they are good for XYZ.”
If someone is using a hammer to cut down a tree, they’re going to have a bad time. A hammer is not a useful tool for that job.
Because you’re using it wrong. It’s good for generative text and chains of thought, not symbolic calculations including math or linguistics
No, I think you mean to say it’s because you’re using it for the wrong use case.
Well this tool has been marketed as if it would handle such use cases.
I don’t think I’ve actually seen any AI marketing that was honest about what it can do.
I personally think image recognition is the best use case as it pretty much does what it promises.
Really? AI has been marketed as being able to count the r’s in “strawberry?” Please link to this ad.
So for something you can’t objectively evaluate? Looking at Apple’s garbage generator, LLMs aren’t even good at summarising.
For reference:
AI chatbots unable to accurately summarise news, BBC finds
It makes me remember I basically stopped using LLMs for any summarization after this exact thing happened to me. I realized that without reading the text, I wouldn’t be able to know whether the output has all the relevant info or if it has some made-up info.
Give me an example of how you use it.
I have it write for me emails in German. I moved there not too long ago, works wonders to get doctors appointment, car service, etc. I also have it explain the text, so I’m learning the language.
I also use it as an alternative to internet search, which is now terrible. It’s not going to help you to find smg super location specific, but I can ask it to tell me without spoilers smg about a game/movie or list metacritic scores in a table, etc.
It also works great in summarizing long texts.
LLM is a tool, what matters is how you use it. It is stupid, it doesn’t think, it’s mostly hype to call it AI. But it definitely has it’s benefits.
We have one that indexes all the wikis and GDocs and such at my work and it’s incredibly useful for answering questions like “who’s in charge of project 123?” or “what’s the latest update from team XYZ?”
I even asked it to write my weekly update for MY team once and it did a fairly good job. The one thing I thought it had hallucinated turned out to be something I just hadn’t heard yet. So it was literally ahead of me at my own job.
I get really tired of all the automatic hate over stupid bullshit like this OP. These tools have their uses. It’s very popular to shit on them. So congratulations for whatever agreeable comments your post gets. Anyway.
One thing which I find useful is to be able to turn installation/setup instructions into ansible roles and tasks. If you’re unfamiliar, ansible is a tool for automated configuration for large scale server infrastructures. In my case I only manage two servers but it is useful to parse instructions and convert them to ansible, helping me learn and understand ansible at the same time.
Here is an example of instructions which I find interesting: how to setup docker for alpine Linux: https://wiki.alpinelinux.org/wiki/Docker
Results are actually quite good even for smaller 14B self-hosted models like the distilled versions of DeepSeek, though I’m sure there are other usable models too.
To assist you in programming (both to execute and learn) I find it helpful too.
I would not rely on it for factual information, but usually it does a decent job at pointing in the right direction. Another use i have is helpint with spell-checking in a foreign language.
Ask it for a second opinion on medical conditions.
Sounds insane but they are leaps and bounds better than blindly Googling and self prescribe every condition there is under the sun when the symptoms only vaguely match.
Once the LLM helps you narrow in on a couple of possible conditions based on the symptoms, then you can dig deeper into those specific ones, learn more about them, and have a slightly more informed conversation with your medical practitioner.
They’re not a replacement for your actual doctor, but they can help you learn and have better discussions with your actual doctor.
sounds like a perfectly sane idea https://freethoughtblogs.com/pharyngula/2025/02/05/ai-anatomy-is-weird/
So can web MD. We didn’t need AI for that. Googling symptoms is a great way to just be dehydrated and suddenly think you’re in kidney failure.
We didn’t stop trying to make faster, safer and more fuel efficient cars after Model T, even though it can get us from place A to place B just fine. We didn’t stop pushing for digital access to published content, even though we have physical libraries. Just because something satisfies a use case doesn’t mean we should stop advancing technology.
We also didn’t make the model T suggest replacing the engine when the oil light comes on. Cars, as it happens, aren’t that great at self diagnosis, despite that technology being far simpler and further along than generative models are. I don’t trust the model to tell me what temperature to bake a cake at, I’m sure at hell not going to trust it with medical information. Googling symptoms was risky at best before. It’s a horror show now.
AI is slower and less efficient than the older search algorithms and is less accurate.
Writing customer/company-wide emails is a good example. “Make this sound better: we’re aware of the outage at Site A, we are working as quick as possible to get things back online”
Dumbing down technical information “word this so a non-technical person can understand: our DHCP scope filled up and there were no more addresses available for Site A, which caused the temporary outage for some users”
Another is feeding it an article and asking for a summary, https://hackingne.ws/ does that for its Bsky posts.
Coding is another good example, “write me a Python script that moves all files in /mydir to /newdir”
Asking for it to summarize a theory or protocol, “explain to me why RIP was replaced with RIPv2, and what problems people have had since with RIPv2”
How does this work in practice? I suspect you’re just going to get an email that takes longer for everyone to read, and doesn’t give any more information (or worse, gives incorrect information). Your prompt seems like what you should be sending in the email.
If the model (or context?) was good enough to actually add useful, accurate information, then maybe that would be different.
I think we’ll get to the point really quickly where a nice concise message like in your prompt will be appreciated more than the bloated, normalised version, which people will find insulting.
Yes, people are using it as the least efficient communication protocol ever.
One side asks an LLM to expand a summary into a fluff filled email, and the other side asks an LLM to reduce the long email to a summary.
Yeah, normally my “Make this sound better” or “summarize this for me” is a longer wall of text that I want to simplify, I was trying to keep my examples short. Talking to non-technical people about a technical issue is not the easiest for me, AI has helped me dumb it down when sending an email, and helps correct my shitty grammar at times.
As for accuracy, you review what it gives you, you don’t just copy and send it without review. Also you will have to tweak some pieces that it gives out where it doesn’t make the most sense, such as if it uses wording you wouldn’t typically use. It is fairly accurate though in my use-cases.
Hallucinations are a thing, so validating what it spits out is definitely needed.
Another example: if you feel your email is too stern or gives the wrong tone, I’ve used it for that as well. “Make this sound more relaxed: well maybe if you didn’t turn off the fucking server we wouldn’t of had this outage!” (Just a silly example)
I think these are actually valid examples, albeit ones that come with a really big caveat; you’re using AI in place of a skill that you really should be learning for yourself. As an autistic IT person, I get the struggle of communicating with non-technical and neurotypical people, especially clients who you have to be extra careful with. But the reality is, you can’t always do all your communication by email. If you always rely on the AI to correct your tone or simplify your language, you’re choosing not to build an essential skill that is every bit as important to doing your job well as it is to know how to correctly configure an ACL on a Cisco managed switch.
That said, I can also see how relying on the AI at first can be a helpful learning tool as you build those skills. There’s certainly an argument that by using tools, but paying attention to the output of those tools, you build those skills for yourself. Learning by example works. I think used in that way, there’s potentially real value there.
Which is kind of the broader story with Gen AI overall. It’s not that it can never be useful; it’s that, at best, it can only ever aspire to “useful.” No one, yet, has demonstrated any ability to make AI “essential” and the idea that we should be investing hundreds of billions of dollars into a technology that is, on its best days, mildly useful, is sheer fucking lunacy.
I have a blog for you
Noted, I’ll be giving that a proper read after work. Thank you.
Edit to add: Yeah, that pretty much mirrors my own experiences of using AI as a coding aid. Even when I was learning a new language, I found that my comprehension of the material very quickly outstripped whatever ChatGPT could provide. I’d much rather understand what I’m building because I built it myself. A lot of the time, when you use a solution someone else provided you don’t find out until much later how badly that solution held you back because it wasn’t actually the best way to tackle the problem.
The dumbed down text is basically as long as the prompt. Plus you have to double check it to make sure it didn’t have outrage instead of outage just like if you wrote it yourself.
How do you know the answer on why RIP was replaced with RIPv2 is accurate and not just a load of bullshit like putting glue on pizza?
Are you really saving time?
Dumbed down doesn’t mean shorter.
If the amount of time it takes to create the prompt is the same as it would have taken to write the dumbed down text, then the only time you saved was not learning how to write dumbed down text. Plus you need to know what dumbed down text should look like to know if the output is dumbed down but still accurate.
it’s not good for summaries. often gets important bits wrong, like embedded instructions that can’t be summarized.
My experience has been very different, I do have to sometimes add to what it summarized though. The Bsky account mentioned is a good example, most of the posts are very well summarized, but every now and then there will be one that isn’t as accurate.
Here’s a bit of code that’s supposed to do stuff. I got this error message. Any ideas what could cause this error and how to fix it? Also, add this new feature to the code.
Works reasonably well as long as you have some idea how to write the code yourself. GPT can do it in a few seconds, debugging it would take like 5-10 minutes, but that’s still faster than my best. Besides, GPT is also fairly fluent in many functions I have never used before. My approach would be clunky and convoluted, while the code generated by GPT is a lot shorter.
If you’re well familiar with the code you’ve working on, GPT code will be convoluted by comparison. If so, you can ask GPT for the rough alpha version, and you can do the debugging and refining in a few minutes.
That makes sense as long as you’re not writing code that needs to know how to do something as complex as …checks original post… count.
It can do that just fine, because it has seen enough examples of working code. It can’t directly count correctly, sure, but it can write “i++;”, incrementing a variable by one in a loop and returning the result. The computer running the generated program is going to be doing the counting.
“You’re holding it wrong”
This but actually. Don’t use an LLM to do things LLMs are known to not be good at. As tools various companies would do good to list out specifically what they’re bad at to eliminate requiring background knowledge before even using them, not unlike needing to somehow know that one corner of those old iPhones was an antenna and to not bridge it.
Yup, the problem with that iPhone (4?) wasn’t that it sucked, but that it had limitations. You could just put a case on it and the problem goes away.
LLMs are pretty good at a number of tasks, and they’re also pretty bad at a number of tasks. They’re pretty good at summarizing, but don’t trust the summary to be accurate, just to give you a decent idea of what something is about. They’re pretty good at generating code, just don’t trust the code to be perfect.
You wouldn’t use a chainsaw to build a table, but it’s pretty good at making big things into small things, and cleaning up the details later with a more refined tool is the way to go.
That is called being terrible at summarizing.
That depends on how you use it. If you need the information from an article, but don’t want to read it, I agree, an LLM is probably the wrong tool. If you have several articles and want go decide which one has the information you need, an LLM is a pretty good option.
if you want to find a few articles out of a few hundred that are about the benefits of nuclear weapons or other controversial topics that have significant literature on them it can be helpful to eliminate 90% that probably aren’t what I’m looking for.
Or you might eliminate some that are what you are looking for because the summaries are inaccurate.
Guess it depends on whether an unreliable system is still better than being overwhelmed with choices.
I think there’s a fundamental difference between someone saying “you’re holding your phone wrong, of course you’re not getting a signal” to millions of people and someone saying “LLMs aren’t good at that task you’re asking it to perform, but they are good for XYZ.”
If someone is using a hammer to cut down a tree, they’re going to have a bad time. A hammer is not a useful tool for that job.