I tend to skim the whole article as I’m often interested in a bit of context and the occasional juicy quote, and I’m interested in the history of a thing. The abstract guides me to the article. I’m generally not one of the 60% who are liars.
I use 2 undermine.ai to provide a detailed summary and things like timing of research. Bought a years sub but won't renew as ai has improved so much.
Also use this prompt.
-----------
Assume the reader is graduate-level knowledgeable about mathematics,
energy economics, renewable energy industry, chemistry, machine learning, building houses, growing plants, artistic design, and typography.
Summarize the following text in.to key points and notable insights:
Please provide:
1. The date the article was published (or note if it is not available)
2. A bullet-point list of the main key points
3. A short paragraph highlighting the most notable insights
4. assume every article has a slant: highlight any misleading or incorrect information
5. If the article is about a recipe, extract just the ingredients and steps involved. If it is about a product, extract the key features and benefits. If there are prices, include them, and also compute a unit cost if possible.
I have started using Consensus which will grade papers for you based on reliability, robustness of research, provides links, citations etc. Previously I only used PubMed, and then also started using AI Assistant in Adobe which was useful for summarising key points or pulling out key points from papers if you were looking for something specific. Also helpful if needing to scan say an insurance document to check if particular clauses are included.
Very interesting. I’m retired and worked in a different field (biochemistry/molecular genetics). I still read a lot of papers, only more broadly than when I was working. Such are the perks of retirement.
Sometimes, reading the Abstract of a paper is sufficient of course, depending on one’s purpose.
I notice you didn’t mention PubMed. The Advanced search function is quite powerful and useful in my area.
When I'm doing anything like that I use manus to do thre first research then push the result into genspark and ask it to double check every reference and flag any other possible problems. So far has worked well. Also I have set up several different identity versions of myself and ask it write as one of them. I'm surprised at how good it is at extrapolating my position on new issues based on my earlier writings.
i also don't know an easy way to set up identity versions of myself. I've been pointing Deep Research to my own publications and asking for literature in support or opposition
I'll message a longer reply rather than clutter up your post but basically they are both chinese, more or less and when I first joined you had to be invited to join, maybe different now. I have consistently found them better, less hallucinations. But I try out as many different models as I can, I used to test endless different linux models as a nerdy hobby, now I try out different LLMs.
I thought the whole point of the Turing Test was that you couldn't tell if you were conversing with a human. LLMs simply proved that given enough capacity and training it isn't that hard to crank out sparkling conversation.
This whole population collapse thing is deeply weird to me, a sublimation of all the other reasons we can expect a population dip, collapse, crash, whatever. The handwaving about fertility smacks of some kind of scam.
I tend to skim the whole article as I’m often interested in a bit of context and the occasional juicy quote, and I’m interested in the history of a thing. The abstract guides me to the article. I’m generally not one of the 60% who are liars.
I use 2 undermine.ai to provide a detailed summary and things like timing of research. Bought a years sub but won't renew as ai has improved so much.
Also use this prompt.
-----------
Assume the reader is graduate-level knowledgeable about mathematics,
energy economics, renewable energy industry, chemistry, machine learning, building houses, growing plants, artistic design, and typography.
Summarize the following text in.to key points and notable insights:
Please provide:
1. The date the article was published (or note if it is not available)
2. A bullet-point list of the main key points
3. A short paragraph highlighting the most notable insights
4. assume every article has a slant: highlight any misleading or incorrect information
5. If the article is about a recipe, extract just the ingredients and steps involved. If it is about a product, extract the key features and benefits. If there are prices, include them, and also compute a unit cost if possible.
Text follows:
Thse prompt suggestions are v helpful, thanks
I have started using Consensus which will grade papers for you based on reliability, robustness of research, provides links, citations etc. Previously I only used PubMed, and then also started using AI Assistant in Adobe which was useful for summarising key points or pulling out key points from papers if you were looking for something specific. Also helpful if needing to scan say an insurance document to check if particular clauses are included.
Very interesting. I’m retired and worked in a different field (biochemistry/molecular genetics). I still read a lot of papers, only more broadly than when I was working. Such are the perks of retirement.
Sometimes, reading the Abstract of a paper is sufficient of course, depending on one’s purpose.
I notice you didn’t mention PubMed. The Advanced search function is quite powerful and useful in my area.
When I'm doing anything like that I use manus to do thre first research then push the result into genspark and ask it to double check every reference and flag any other possible problems. So far has worked well. Also I have set up several different identity versions of myself and ask it write as one of them. I'm surprised at how good it is at extrapolating my position on new issues based on my earlier writings.
I don't know either manus or genspark. Links?
i also don't know an easy way to set up identity versions of myself. I've been pointing Deep Research to my own publications and asking for literature in support or opposition
I'll message a longer reply rather than clutter up your post but basically they are both chinese, more or less and when I first joined you had to be invited to join, maybe different now. I have consistently found them better, less hallucinations. But I try out as many different models as I can, I used to test endless different linux models as a nerdy hobby, now I try out different LLMs.
I thought the whole point of the Turing Test was that you couldn't tell if you were conversing with a human. LLMs simply proved that given enough capacity and training it isn't that hard to crank out sparkling conversation.
This whole population collapse thing is deeply weird to me, a sublimation of all the other reasons we can expect a population dip, collapse, crash, whatever. The handwaving about fertility smacks of some kind of scam.