Seneca
AI
chatbot
SHOW HN2023
How HN took it
11 positive, 31 neutral or asking, 1 mixed, 21 critical, out of 64 comments about the project. Thread score -0.15.
Execution: 2 for, 16 againstIdea: 6 for, 3 againstPrivacy: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Answers are quoted and sourced from Stoic texts
From 2 comments
wow, this is cool, quotes are sourced! :)
globuous on HNLove it, results are legit. > How should we deal with the inevitable threat of death? ``` Friend, death is an inevitable part of life that we must accept. We should strive to…
amoss on HN
Fun to try and nostalgic for philosophy study
From 2 comments
Love it, results are legit. > How should we deal with the inevitable threat of death? ``` Friend, death is an inevitable part of life that we must accept. We should strive to…
amoss on HNAh you beat me to it! I had thought about doing this but with all sorts of philosophers / materials. Really nice!
petargyurov on HN
Objections
Possible fabricated or confabulated quotes
From 1 comment
Cool! One of the first things I did with GPT3 was fine tune it with the complete works of Plato. It works only with a lot of mediation. This appears to be made with a prompt…
dr_dshiv on HN
Requests
Share the code or repo
From 1 comment
If it's public, Can you share the repo? This is really good, and I'd love to see how you did it. I imagine you are using a vector store/search on the backend, just cutrious!
pstorm on HN
Explain the fine-tuning or prompting method
From 2 comments
Would love a breakdown on how this fine-tuning is accomplished. What was the format of the input data? How many prompt/response pairs was it fine-tuned on? Where/how did you…
tevon on HNCool! One of the first things I did with GPT3 was fine tune it with the complete works of Plato. It works only with a lot of mediation. This appears to be made with a prompt…
dr_dshiv on HN
Support response streaming in Node
From 1 comment
Very nice. Are you using NodeJS? Apparently the Python bindings do support streaming the responses, but not the Node ones (yet?). Was curious if anyone had found/built a…
andai on HN
Questions
Is it few-shot prompting or fine-tuning, and how is sourcing done?
From 3 comments
Is this using few shot prompting?
braindead_in on HNCool! One of the first things I did with GPT3 was fine tune it with the complete works of Plato. It works only with a lot of mediation. This appears to be made with a prompt…
dr_dshiv on HNIs this not using embeddings? A corpus of material was fed into embeddings, when a question is asked you query the vectorized embeddings and then pass the n relevant texts into…
infecto on HN
What front end was used?
From 1 comment
Looks cool. What did you use to build the front end?
pruthvishetty on HN
Alternatives named
Embeddings-based question answering with OpenAI
From 1 comment
Is this not using embeddings? A corpus of material was fed into embeddings, when a question is asked you query the vectorized embeddings and then pass the n relevant texts into…
infecto on HN
Replika
From 1 comment
Too late, Replika used GPT-3 in 2020 and it was marketed under the health section of the Google Play store.
bezier-curve on HN