Tried to use openrouter with web search with Grok for this purpose yesterday. It got the date right but all of the news was months old, like the Mt. Etna eruption.
It’s pretty disappointing. It seems like a “trivial” task
AI assistants misrepresent news content 45% of the time
301–306 of 306 posts
Re: AI assistants misrepresent news content 45% of the time
#302How often is the "news content" misrepresenting its sources?
Re: AI assistants misrepresent news content 45% of the time
#303These problems are well known for a long time, especially if one simply asks LLM for a changing fact, such as who is the current pope.
But there is also a simple technique that reduces these issues almost to zero: thinking and explicit request of grounding.
For example, asking any LLM: who is the current pope could give a wrong answer due to the fact that Pope Francis died in April 2025 then the cut-off date of these models may be before that date. A simple question triggers simple associations, and so the answer could be wrong. But if turn on the thinking mode and instruct for grounding, the LLM will answer correctly.
For the above example, asks instead: "Who is the current pope? Ground your answer on trustworthy external sources only" with thinking mode on or explicitly "think harder for better answer", all popular AI (ChatGPT 5+, Gemini 2.5 Flash, Claude 4+, Grok 4+) will answer correctly, albeit with sometimes long thinking time (28 s by ChatGPT 5 for example).
Without explicit instructions, the accuracy of the result depends heavily on the cut-off date and default settings of each model. Grok 4, for example, in auto-mode will do a search then answer correctly, but Grok 3 will not.
Re: AI assistants misrepresent news content 45% of the time
#304Kagi News has been pretty accurate. Source information is provided along with the summary and key details too. AI summarizes are good for getting a feel of if you want to read an article or not. Even with Kagi News I verify key facts myself.
agreed on Kagi News, and Particle News has been good, but they accepted funding from The Atlantic which evidently earns "Featured Article" positioning to articles from funding sources, muddying the clarity of biases, which Particle News has a nice graphic indicator for, though i've not seen it under promoted Feature Articles. Surely applies to other funding sources, but The Atlantic one was pretty recent.
fwiw Particle News is paying publishers to run their full text content in the Particle app and this is just a staff pick. unfortunate that it gave the opposite impression of being an ad
Re: AI assistants misrepresent news content 45% of the time
#305Earlier quoted context omitted.
agreed on Kagi News, and Particle News has been good, but they accepted funding from The Atlantic which evidently earns "Featured Article" positioning to articles from funding sources, muddying the clarity of biases, which Particle News has a nice graphic indicator for, though i've not seen it under promoted Feature Articles. Surely applies to other funding sources, but The Atlantic one was pretty recent.
fwiw Particle News is paying publishers to run their full text content in the Particle app and this is just a staff pick. unfortunate that it gave the opposite impression of being an ad
that's interesting.
Re: AI assistants misrepresent news content 45% of the time
#306Earlier quoted context omitted.
It makes me think that a lot of the folks commenting on this stuff haven't actually used the tooling. Agreed, it's generally quite accurate. I find for hectic meetings, it can get some things wrong... But the notes are generally still higher quality than human generated notes. Is it perfect? No. Is it good enough? IMO absolutely. Similar to many other things, the key is that you don't just blindly trust it. Have the…
I think the cost of inaccuracy is very a important factor in if it works for a specific use case. Meeting notes probably don't have much cost of inaccuracy. Medical records on the other hand...
Absolutely, I was just using this example in response to someone who specifically mentioned meeting notes. That’s an area where LLMs are a clear benefit ime.