Compress GPT-4 Prompts
AI
prompt compression
SHOW HN2023
How HN took it
2 positive, 11 neutral or asking, 1 mixed, 16 critical, out of 30 comments about the project. Thread score -0.40.
Idea: 0 for, 6 againstPerformance: 1 for, 3 againstExecution: 1 for, 3 againstPricing: 0 for, 3 againstDocs: 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
Interesting idea, could help context windows or local models
From 2 comments
This looks interesting if it works. A side benefit of prompt hacking like this appears when you transition from OpenAI to local, cost-static models, too. Losslessly minimizing…
drusepth on HNTried twice and didn't get usable results. The first reduced the tokens by 80% and the results were better than I would've expected. The second try reduced the same prompt by…
wfhBrian on HN
Objections
Compressed prompts often do not reduce tokens and can increase them
From 3 comments
The original tweet author eventually realized this didn't decrease tokens. In most cases it actually increases them compared to just asking GPT to summarize while retaining all…
ddod on HNThe gnarly thing is that common dictionary words are usually 1 or 2 tokens (a whole word, or a stem + a suffix), while things like emojis end up as _3_ tokens.…
cheald on HNI was hoping I could use this to reduce the cost of using the openai API. But since it sends both the custom prompt telling gpt4 to compress the intent and the full original…
superkuh on HN
Compressed prompts lose meaning and do not work reliably
From 3 comments
I gave it the prompt: > Explain the first law of robotics while speaking like a pirate, and in enough carefully considered detail that a seven year old child could understand The…
mistercow on HNThis should just be deleted. I'm sorry, but it doesn't work reliably, hardly compresses the prompt, and is going to mislead people
weird-eye-issue on HNYeah except this doesn't actually work reliably.
weird-eye-issue on HN
Sending the full prompt to compress it means no net savings
From 2 comments
It's kind of hilarious that you're trying to charge money for this. Given that compressing the prompt requires putting the full prompt into GPT-4, it's mathematically impossible…
abitnegative on HNI was hoping I could use this to reduce the cost of using the openai API. But since it sends both the custom prompt telling gpt4 to compress the intent and the full original…
superkuh on HN
Requests
Remove the claim that results stay the same
From 1 comment
> Reduce the number of tokens used in GPT-4 prompts by half and still get the same results! I would erase “and still get the same results” completely until you’re certain it can…
ShamelessC on HN
Questions
Does this reduce token count?
From 1 comment
Does this reduce token count?
quickthrower2 on HN
Alternatives named
Asking GPT to summarize the prompt
From 1 comment
So they are using the following GPT-4 prompt: -- compress the following text in a way that fits in a tweet (ideally) and such that you (GPT-4) can reconstruct the intention of…
highfreq on HN