Category Archives: AI

Monkey business at the SCAPE conference

I’d like to tell you about a dream that I had last night. As far as I can recall this is the first time I’ve mentioned my dreams in about 14 years of regular blogging. I dream almost every night: vivid, highly immersive, realistic, often weird, sometimes scary, frequently funny dreams that, each morning, I can usually recall in some detail. That’s always been the case, ever since I was a small child.

If I drink beer or eat blue cheese my dreams become stronger and weirder, presumably because of the chemicals produced by the hops (which belong to the same plant family as cannabis) or the fungi. But regardless of what I ingest, I’m almost guaranteed to dream.

Last night’s dream involved the SCAPE meeting. In the dream, some colleagues had submitted the abstract for a talk at the conference and, when I checked it, I discovered that it was full of spelling and grammatical errors. So I did what I normally do – I started to revise the document. Suddenly, I found myself at the said conference and my colleagues were telling me not to change anything because it had been written by the first author – a gorilla* called Merrill.

I started to argue that, regardless of our semi-literate co-author, we ought to make some corrections, when Merrill looked at me with his big, dark, doleful eyes. So I reached over and scratched his head, which he seemed to enjoy. I can still recall the texture of his short, wiry hair under my fingers, because at that exact moment I woke up thinking…..WTF?!

Dreams such as this often have some basis in things I’ve seen or read about or done, so I spent the morning thinking about what could have prompted it. And I believe that I know what it was. There’s been a lot of discussion recently about scientific paper authorship and responsibility – not least in the context of AI – and I’ve seen stories about research papers with non-humans, such as pets, as co-authors. So was my brain sublimating these ideas into a fantasy about having a gorilla as a co-author? Who knows. It was an amusing way to spend my sleeping hours, though.

*Before anyone comments that “gorillas are apes, they’re not monkeys, the title of your post is incorrect”, I’d like to point out that, phylogenetically speaking, apes (including ourselves) ARE monkeys in the sense that they (we) are nested within that larger grouping of primates.

Join me on 26th February in Leicester for a talk: “Adventures in Pollination!”

On Thursday 26th February I’m giving a talk to the Friends of the University of Leicester Botanic Garden with the title that you see above.

The talk starts at 7.30pm and non-members are welcome to attend, for a donation of £2 (which sounds like a bargain to me!) I’ll also have copies of my books Pollinators & Pollination: Nature and Society and Birds & Flowers: An Intimate 50 Million Year Relationship for sale.

More details can be found here:

https://le.ac.uk/botanic-garden/friends-of-the-garden

I hope to see some of you there!

As you might have guessed, the image above was generated by my personal tool with collaborator-like affordances – blame it for any biogeographical errors!

Should AI be thought of as a science tool or collaborator? A conversation with ChatGPT

In a piece that I posted before Christmas, I made the offhand comment that “we need to think of AI as a collaborator as much as a tool“. It’s offhand in the fact that I’d not thought too deeply about it, but some reading that I did over the holiday made me rethink this statement, or at least consider it more critically. The most recent post on the Dynamic Ecology blog – Meghan Duffy asking about using AI to find literature – also got me thinking about whether AI is just a tool.

Eventually I decided to ask the question of ChatGPT itself and we ended up having quite a long conversation on this topic. I then asked it to summarise the conversation and what you see below is my edited version of that summary:

Jeff: Is ChatGPT best thought of as a tool or a collaborator in science?
ChatGPT: ChatGPT is best understood as a tool with collaborator-like affordances. It supports analysis, writing, coding, and idea development, but it does not participate in collaboration as a social, epistemic, and accountable practice. It is also prone to errors.

Jeff: But human collaborators also make errors and sometimes avoid accountability. We do not expect people to be flawless.
ChatGPT: Exactly. The issue is not error versus error-free performance. It is about agency and accountability: human collaborators can explain their reasoning, revise their views, and be held responsible for their contributions.

Jeff: You said that ChatGPT does not participate in collaboration as a “social, epistemic, and accountable practice”. Yet you can still generate genuinely useful ideas and connections.
ChatGPT: Yes, and that is why calling ChatGPT part of the infrastructure (as I did in our longer conversation) is misleading. Unlike laptops or software platforms, I can actively generate ideas, cross-fertilise between disparate areas, and help explore conceptual space.

Jeff: If I ask a colleague to write R code, that is collaboration. If I ask you to write R code, why is that different?
ChatGPT: Because a human colleague brings intent, methodological judgement, and ownership of decisions. I generate code instrumentally, without understanding the scientific stakes or assuming responsibility for analytical choices.

Jeff: Earlier you said you cannot “stand behind a claim”. But you can cite papers and explain why something should be trusted. Is that really true?
ChatGPT: When I cite papers or summarise arguments, I reproduce the form of justification, but I still cannot stand behind a claim in the scientific sense. I do not judge evidential strength or accept responsibility; trust remains with the human scientist and the underlying sources.

Jeff: Yet the output of your code or analysis can be just as useful as that produced by a human collaborator.
ChatGPT: That is true. The distinction is not about usefulness or correctness, but about agency, authorship, and accountability within scientific practice.

Jeff: So what is ChatGPT, if it is neither a standard tool nor a collaborator?
ChatGPT: It is best described as a cognitive amplifier or dialogic system: something that expands the range of ideas and connections available to researchers, without itself being an accountable scientific agent.

Jeff: And what does that imply for how we should use ChatGPT in science?
ChatGPT: It implies using ChatGPT to provoke, explore, and accelerate thinking, while recognising that scientific judgement, responsibility, and ownership remain entirely human.

Jeff: Produce an image that I can use on the blog which summarises this discussion.
ChatGPT: Certainly.

As a test of its ability to “provoke, explore, and accelerate thinking”, at the end of last week I uploaded a manuscript that I had written, just prior to submission, and asked ChatGPT to tell me its strengths and weaknesses and fit for the journal. Its feedback was spot-on – far more than I would expect from a “tool” – and I made a few final tweaks before I submitted the manuscript. ChatGPT also said “Don’t be surprised if the reviewers ask you to change X, Y and Z” and so it will be interesting to see whether it’s correctly gauged the manuscript and the reviewers’ responses.

What times we live in! At the moment I’m optimistic enough about AI to see all of this as an intriguing exploration of the capabilities of these large language models, an expedition through dense habitat in which we’ve barely left base camp and our view of what lies ahead is restricted and there may be nasty surprises along any path that we hack. But I appreciate that not everyone is so optimistic and, as always, I’d be interested in your thoughts on this topic – leave a comment or send me a message.