Add a comparison table between your repo and alternatives like rtk. I’m interested.
Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
51–60 of 97 posts
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#52I would like to have deeper comparison with alternatives like rtk, which are already fast and written in rust, also the previous comments mentioned something that has been a know problem with rtk that it sometimes strips the thing that the llm needs (or expects, causing more work to need to happan not less)
None of these tools measure how effective they are... It's a massive red flag to me when you could get decent data to see if your thing actually works, and they don't even attempt to... Have the LLM use your tool, run it on several of the coding benchmarks. If you're stingy, run it on the ones that don't cost much. Otherwise, I'm going to assume it doesn't actually work. If it did - Claude, Antigravity, Codex, Pi, or…
This is the reason, when I built a tool in the same space, I chose to benchmark with cost per correct answer.
Reducing tokens and also turns is quite worthless if the LLM doesn’t solve what you put it to do.
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#53Earlier quoted context omitted.
None of these tools measure how effective they are... It's a massive red flag to me when you could get decent data to see if your thing actually works, and they don't even attempt to... Have the LLM use your tool, run it on several of the coding benchmarks. If you're stingy, run it on the ones that don't cost much. Otherwise, I'm going to assume it doesn't actually work. If it did - Claude, Antigravity, Codex, Pi, or…
This is the reason, when I built a tool in the same space, I chose to benchmark with cost per correct answer. Reducing tokens and also turns is quite worthless if the LLM doesn’t solve what you put it to do.
Did you benchmark the competition and can we see?
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#54Great! Now, you should slap a logo to this, boostrap this as a service, and get you some YC funding. [0]
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#55I would like to have deeper comparison with alternatives like rtk, which are already fast and written in rust, also the previous comments mentioned something that has been a know problem with rtk that it sometimes strips the thing that the llm needs (or expects, causing more work to need to happan not less)
None of these tools measure how effective they are... It's a massive red flag to me when you could get decent data to see if your thing actually works, and they don't even attempt to... Have the LLM use your tool, run it on several of the coding benchmarks. If you're stingy, run it on the ones that don't cost much. Otherwise, I'm going to assume it doesn't actually work. If it did - Claude, Antigravity, Codex, Pi, or…
> otherwise, popular solutions would integrate the idea
None of the major players are incentivized to care about this, especially not over other opportunities. Why would you expect them to integrate it?
One of the biggest wins you can institute for your own codebase if you use agents is writing your own harness, by a huge margin. The defaults are fine, but you can do better.
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#56[flagged]
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#57Earlier quoted context omitted.
This is the reason, when I built a tool in the same space, I chose to benchmark with cost per correct answer. Reducing tokens and also turns is quite worthless if the LLM doesn’t solve what you put it to do.
Did you benchmark the competition and can we see?
The problem even attempting to develop a tool for the frontier model space is that the cost to run a statistically significant benchmark is almost certainly going to be over $100 - for a single model.
Unless something is like 25%+ more cost effective on Gemini for a task, I would not assume those savings are going to transfer to GPT.
If you need to run a test this expensive and slow for every release, hobbiests aren't going to do it.
And if you wanted any broadly specific improvements to coding like they all claim, the costs would be in the thousands per release even for a single for a single model.
And they almost certainly would not be eye popping.
If the models could be SUBSTANTIALLY better, Google and Anthropic and OpenAI wouldn't be finding that out from a hobbiest making wildly unscientific claims.
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#58Earlier quoted context omitted.
None of these tools measure how effective they are... It's a massive red flag to me when you could get decent data to see if your thing actually works, and they don't even attempt to... Have the LLM use your tool, run it on several of the coding benchmarks. If you're stingy, run it on the ones that don't cost much. Otherwise, I'm going to assume it doesn't actually work. If it did - Claude, Antigravity, Codex, Pi, or…
> otherwise, popular solutions would integrate the idea None of the major players are incentivized to care about this, especially not over other opportunities. Why would you expect them to integrate it? One of the biggest wins you can institute for your own codebase if you use agents is writing your own harness, by a huge margin. The defaults are fine, but you can do better.
> The defaults are fine, but you can do better.
Why can I do better than Pi?
I don't want to build my own harness and deal with the bugs... I want to build my project...
My understanding is that Codex / Claude / Gemini subscriptions don't work with custom harnesses.
It's pretty hard to beat 5x more usage if you have the $200/mo subscription by using the API instead.
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#59Earlier quoted context omitted.
> otherwise, popular solutions would integrate the idea None of the major players are incentivized to care about this, especially not over other opportunities. Why would you expect them to integrate it? One of the biggest wins you can institute for your own codebase if you use agents is writing your own harness, by a huge margin. The defaults are fine, but you can do better.
> The defaults are fine, but you can do better. Why can I do better than Pi? I don't want to build my own harness and deal with the bugs... I want to build my project... My understanding is that Codex / Claude / Gemini subscriptions don't work with custom harnesses. It's pretty hard to beat 5x more usage if you have the $200/mo subscription by using the API instead.
Codex definitely does and Claude Max definitely doesn’t.
Re: Show HN: Lowfat – pluggable CLI filter that saved 91.8% of my LLM tokens
#60This is a nice little project but I’m weary of sensationally inaccurate titles for stuff like this and the infamous caveman mode. It doesn’t save 91% of tokens: it reduced in one user case 91% of output tokens on the raw CLI output. I am being pedantic about this because these sorts of claims go viral and are inaccurate. A proper benchmark will compare a large sample of identical prompting with and without the tool,…
Understood. Didn't mean as a click-bait or something. Just sharing my cli report summarize.
Target user here in HN should be tech-savy and this tool is not designed for non-tech because it is required highly customized from user to get the result user want.
Anway, would you mind putting the correct title here ? I will consider to update.