Needs audio input and output, so that we can de-bulshittify political speechs on the fly.
I think the output would be empty "".
Show HN: Bullshit Remover
91–100 of 157 posts
Re: Show HN: Bullshit Remover
#92If you applied this to the internet, 90% of it would vanish in seconds. Think of the vast amounts of energy saved!
Re: Show HN: Bullshit Remover
#93Coca Cola - Can’t beat the feeling Sugar water - Can’t beat diabetes
Seems to have some real world knowledge
Re: Show HN: Bullshit Remover
#94Earlier quoted context omitted.
Here’s what I got: Translate from bullshit to no-bullshit. Be funny and sarcastic. Shorten text. Remove bullshit, don't explain. Return response in the same language as input. Return only response.
Just so I understand: this HN post consists of a 6-sentence plain English prompt, and a web app that passes the prompt plus presumably raw user input to a black box LLM API? Is there more?
Welcome to the LLM API wrapper future. This is basically what 99% of the "AI startups" do.
Re: Show HN: Bullshit Remover
#95Earlier quoted context omitted.
Here’s what I got: Translate from bullshit to no-bullshit. Be funny and sarcastic. Shorten text. Remove bullshit, don't explain. Return response in the same language as input. Return only response.
Just so I understand: this HN post consists of a 6-sentence plain English prompt, and a web app that passes the prompt plus presumably raw user input to a black box LLM API? Is there more?
Just so I understand: you’re talking about setting up an FTP account, using curlftpfs, and SVN/CVS for Linux users? And even with all these, you’d still need USB drives for connectivity issues? Plus, you're naming it Dropbox? Is there more?
Re: Show HN: Bullshit Remover
#96Looks like these are the instructions: " Translate from bullshit to no-bullshit. Be funny and sarcastic. Shorten text. Remove bullshit, don't explain. Return response in the same language as input. Return only response. " I'm surprised it works so well with so few instructions! What underlying model are you using? Edit: After digging further, it looks like it's using an Anthropic model. Really nice.
As upper-mentioned, I'm using Claude 3.5 Sonnet.
Nice that you were able to get instructions
Re: Show HN: Bullshit Remover
#97This is hilarious. I think it could also be a serious tool - without the added snark. I'd pay for a version of this that allowed me to look at product pages and just get the facts without the manipulative bullshit.
How would you like it for serious tool? Is website enough or you would like to have it as a browser extension?
Btw. for longer text it's less ironic, focused more on removing bullshit.
Re: Show HN: Bullshit Remover
#98This is hilarious. I think it could also be a serious tool - without the added snark. I'd pay for a version of this that allowed me to look at product pages and just get the facts without the manipulative bullshit.
Would't that work by just asking chatgpt or similar to summarize and remove the buzzwords? (I rarely use these tools so I do not know if they are efficient in such tasks)
The difficult part would be keeping it working after it gets popular, and all the marketers in the world try to break it.
Re: Show HN: Bullshit Remover
#99This is hilarious. I think it could also be a serious tool - without the added snark. I'd pay for a version of this that allowed me to look at product pages and just get the facts without the manipulative bullshit.
How would you like it for serious tool? Is website enough or you would like to have it as a browser extension? Btw. for longer text it's less ironic, focused more on removing bullshit.
Cool, I'll try it with some longer text
As a browser extension would be most usable (although I'd have to think about the privacy issues with that).
Re: Show HN: Bullshit Remover
#100This would make for a handy chrome plugin.
I'll consider it :)