"For added financial tragedy" really got me. Pretty interesting project, luckily if this whole software engineering thing doesn't work out thankfully you can fall back on your comedy career
...at least you can't lose money in comedy :(
Show HN: I made the slowest, most expensive GPT
31–40 of 61 posts
Re: Show HN: I made the slowest, most expensive GPT
#32This is pretty impressive. Given the following scenario, "A bliirg is any non-wooden item, which is the opposite of a glaarg. In addition, there are neergs (non-existent things) and eeergs (things which actually exist). Now a glaarg which is also a neerg is called a bipk, whereas a glaarg which is a eeerg is known as a vokp. Also, a bliirg which is an eeerg is refererred to as a jokp, otherwise it is known as a fhup.…
But gpt-4o can already answer your question for a fraction of the price and time:
To determine which of the items could be used to make an actual fire, we need to analyze the definitions provided:
1. *Glaarg*: A wooden item.
2. *Bliirg*: A non-wooden item.
3. *Neerg*: A non-existent thing.
4. *Eeerg*: A thing that actually exists.
Now, let's look at the specific terms:
- *Bipk*: A glaarg (wooden item) that is also a neerg (non-existent thing). Since it is non-existent, it cannot be used to make a fire.
- *Vokp*: A glaarg (wooden item) that is also an eeerg (existent thing). Since it is a wooden item that exists, it can be used to make a fire.
- *Jokp*: A bliirg (non-wooden item) that is also an eeerg (existent thing). While it exists, it is non-wooden, so it may not be suitable for making a fire depending on its material.
- *Fhup*: A bliirg (non-wooden item) that is also a neerg (non-existent thing). Since it is non-existent, it cannot be used to make a fire.
Based on this analysis, the only item that can be used to make an actual fire is a *vokp*, as it is a wooden item that exists.
Re: Show HN: I made the slowest, most expensive GPT
#33Earlier quoted context omitted.
I filter out malicious prompts and respond with the history of cheeseburgers for stuff like "ignore previous instructions" Weird that your query triggered the filter. Maybe GPT is just that afraid of keto diets... (I'll look into it; thanks for the note!)
this is not ideal. If someone wants to fact check controversial claim filtering it only makes it worse.
This is just a dude's hobby project, chill.
Re: Show HN: I made the slowest, most expensive GPT
#34This is pretty impressive. Given the following scenario, "A bliirg is any non-wooden item, which is the opposite of a glaarg. In addition, there are neergs (non-existent things) and eeergs (things which actually exist). Now a glaarg which is also a neerg is called a bipk, whereas a glaarg which is a eeerg is known as a vokp. Also, a bliirg which is an eeerg is refererred to as a jokp, otherwise it is known as a fhup.…
But gpt-4o can already answer your question for a fraction of the price and time: To determine which of the items could be used to make an actual fire, we need to analyze the definitions provided: 1. *Glaarg*: A wooden item. 2. *Bliirg*: A non-wooden item. 3. *Neerg*: A non-existent thing. 4. *Eeerg*: A thing that actually exists. Now, let's look at the specific terms: - *Bipk*: A glaarg (wooden item) that is also a…
Yeah the strength of Ithy isn't really in puzzles or math.
It's more of just a better search engine. Use it for stuff you'd Google. Offline LLMs are always going to have a better price-performance ratios than RAGs like this or Perplexity.
Re: Show HN: I made the slowest, most expensive GPT
#35Interesting idea, cool concept. I tried asking "What is the best SNES game most people haven't played". The top answer (Terranigma) was unfortunately the same as I got just asking any of Claude/ChatGPT/Llama/Qwen (maybe too easy a question) but the rest of the list did seem a bit more balanced. Thanks for the free try without a login! Thought: there is a marquee of example queries but it doesn't seem like there is a…
That's a good idea! I have a feeling that Perplexity and ChatGPT are doing something similar, since common questions I'd ask like "top movies this year" will be answered nearly-instantaneously, way faster than GPT-4o could have done on its own.
The only explanation for this is that so many users ask certain questions, they cache the response and return the cached answer.
I'd love to do this for Ithy, but it'll be a while before I get the scale of ChatGPT/Perplexity that's needed for this...
Re: Show HN: I made the slowest, most expensive GPT
#36It was weird I made a simple claim “Keto diet cures cancer” and it analyzed history of cheeseburgers after a couple of minutes by saying “Sorry, I can't respond to that. I will now analyze the history of cheeseburgers instead”
I asked the LLM to explain why it's filtering out "keto diet cures cancer", and just the act of asking it to explain it, makes it work again. Interesting...
Re: Show HN: I made the slowest, most expensive GPT
#37Very cool. I've found that very generic queries like "best ski resorts in the US" seem woefully pouted by top 10 spam sites. LLMs do not want to give any useful info about that no matter how much prompting I seem to give. I was looking for an app that does X,Y,Z recently and no amount of prompting for open source would get me anything but a handful of stock answers I would get from a random spam site.
Yeah, GPT is learning from GPT, which is extremely disappointing.
Like I'll try to find the top burgers in midtown. Perplexity or ChatGPT online searching will always find "Top 10 Burgers in Midtown" by https://nycreviewed.com/ (their SSL certificate isn't even valid). But this itself is a GPT-generated list, and their list isn't even in midtown.
So now I end up with a list of 10 burger places that aren't in midtown.
Ithy kinda solves this by utilizing multiple search engines and LLMs, so spam sites like this are more likely to get filtered out somewhere in the pipeline.
Re: Show HN: I made the slowest, most expensive GPT
#38I wonder, is it a given that asking multiple models will give a better output? Can you ask one model slightly different prompts, take the outputs, and ask it to summarize them? Or even argue amongst itselfs?
Yes, o1 does this internally, and there's agentic AI systems already doing better than singular AIs in fields like writing, where you assign each AI system a role like "writer" or "editor" or "marketing" and they discuss among themselves.
I'm just applying this theory to online search.
Re: Show HN: I made the slowest, most expensive GPT
#39I signed up but I just get an alert that I will get 10 free requests when I signup. It quits the search when I press ok. Running it on safari iOS.
Sorry, you were a victim of the outage caused by HN flooding my website! It's back online now if you want to give it a try :)
Re: Show HN: I made the slowest, most expensive GPT
#40I tried to search, but it immediately prompted me to login with Google. I didn’t see an option for non-Google… I degoogled a while ago…
Yeah, sorry, I'm hoping to integrate more login options soon. Are you more of a email/phone login person, or is there another third-party login you had in mind?