# Summarising topics with an LLM (GPT, BERT, ...)?

**URL:** <https://meta.discourse.org/t/summarising-topics-with-an-llm-gpt-bert/254951>\
**Category:** Feature\
**Created:** [February 13, 2023, 6:27am UTC](https://meta.discourse.org/t/summarising-topics-with-an-llm-gpt-bert/254951 "2023-02-13T06:27:55Z")\
**Posts on this page:** 1\
**Showing post:** 1

<div class="post-metadata">

**Author:** ![Julienlavigne](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/julienlavigne/32/295051_2.png) [@Julienlavigne](https://meta.discourse.org/u/Julienlavigne)\
**Post date:** [February 13, 2023, 6:27am UTC](https://meta.discourse.org/t/summarising-topics-with-an-llm-gpt-bert/254951/1 "2023-02-13T06:27:55Z")

</div>

Dear discourse team,

Discourse has the ability to summarise long threads. My understanding is that it uses engagement metrics like reactions or number of replies to identify what posts should be kept. In my community (internal communication within the company) this almost never triggers despite threads that are 20 pages long (reply count is not the best trigger for us)

A more powerful approach would be to use an LLM like GPT-3 or BERT to summarise the whole thread on demand (vs just filtering the posts). Summarisation is a use case where LLMs shine (pretty much the poster child) and I believe this would be way more effective than the current approach which is based on weak signals (in some communities, people may not use reactions or reply to specific posts).

On the other hand, running GPT to summarise text can be [expensive](https://openai.com/api/pricing/), up to $0.02 per 1k tokens. This feature would probably make more sense in some private communities than high-traffic public ones.

I imagine the feature to work like this:

- when reading a long thread for the first time (long defined with a setting) that has never been summarised, suggest to summarise it on demand.
- the summarisation would be inserted in the thread (eg: everything before is summarized)
- it is linked from the top of the thread (eg: jump to the summary)
- ideally, there is some 👍 👎 feedback mechanism
- after N more replies, offer to publish a new summary and update the link at the top.
- the plugin would be configured with an openai key (assuming this is the LLM used). Eventually, if it proves successful, you would want to offer access to different models.

At least that’s the theory 🙂. In practice there are unknowns about how good it would be, or how to configure the degree of summarization. My instinct is that this is extremely high ROI for some communities. The number one problem I hear is that people hate catching up on threads. This would be of massive help.

Thoughts?

---

_[View the full topic](https://meta.discourse.org/t/summarising-topics-with-an-llm-gpt-bert/254951)._