It has already been trained on the ASR forum content up to its cut-off date and updates itself "live" (see below: its response is near instantaneous, but it gets my current number of posts/likes correct as of today).
Retraining it on the forum's content is almost pointless imho.
summarize the activity of the PierreV user on the audio science review forum.
ChatGPT
PierreV is an active participant on the Audio Science Review forum, contributing to various discussions related to audio equipment and technology. Here's a summary of PierreV's activity:
- Joined Date and Contribution Level: PierreV, a major contributor and forum donor, joined the forum on November 6, 2018. They have posted 1,435 messages and received 4,682 likes as of February 8, 2021.
- Interests and Purchases: PierreV has purchased several items based on recommendations from the site, including a dacmagic plus, a KTB, and Hypex kits. They highlighted the dacmagic plus's functionality and expressed a desire for improved volume control features.
- Contributions to Discussions: They have engaged in discussions on various topics, including the value of high-resolution audio, the Dunning-Kruger effect, and the comparison of high-end passive bookshelf speakers versus mid-range active studio monitors.
- Technical Insights and Reviews: PierreV has shared insights on specific audio equipment and technology. For example, they discussed the potential overestimation of competences related to the Dunning-Kruger effect within the context of audio science, and provided feedback on the performance and features of audio products like the dacmagic plus.
- Forum Engagement: They actively participate in various threads, reacting to posts, sharing opinions, and contributing to the community's knowledge base. PierreV's contributions span across technical discussions, product reviews, and audio technology analysis.
PierreV's activity on the Audio Science Review forum indicates a deep interest in audio technology, a willingness to engage in technical discussions, and an appreciation for the community's insights on audio equipment. Their contributions reflect both a pursuit of quality audio experiences and a commitment to the forum community.
While not retraining - if
@amirm wants a review thread summary that is up to date (say daily) the LLM needs to be fed the content - in my experience - while it can read a page of content - it typically won't read beyond the first page of the thread - so programmatically submitting the thread posts (or probably selected thread posts e.g. 'liked' posts ) will allow a better summary of the thread.
With the chatGPT API there is also a 'temperature' setting - see below (from their API playground)
Which controls how 'creative' the generated response will be. In these types of summaries, it probably best to 'deterministic and repetitive'.
There are other use cases where the content generated does not need to be as up to date (as your example above) and I did think a 'compare' reviews capability might be very interesting, e.g. take just the review content itself of 2 DAC or 2 Amps (or more than 2) and generate a 'textual' comparison for those you don't like comparing graphs.
But a 'chatbot' to answer audio science questions that only uses content from AudioScienceReview (and doesn't start pulling content from other pages that it was trained on ) would need IMO at the very least need to use 'continous pretraining' capabilities. This is where an existing trained LLM (and it doesn't have to be ChatGPT, CoPilot or Gemini) is 'updated' with domain specific content which it prioritises over other content. But while not as expensive as full training this still a more involved process that using the trained data.