Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by hboon on Friday June 05, 2026 @08:31PM
(#48420142)
Codex definitely does and Claude Max definitely doesn’t.
Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by Bnjoroge on Saturday June 06, 2026 @05:09PM
(#48429029)
definitely doesnt is a strong word. it technically is possible, but you might get banned
Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by hboon on Saturday June 06, 2026 @11:59PM
(#48431637)
That was true. But actually, I think that's changed a few weeks ago since they introduced a API credit amount equivalent to your (eg. $100, $200) that will be used for such cases. So they don't ban you, they just bill you that allocated credit and then actual API cost.
Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by Bnjoroge on Tuesday June 09, 2026 @01:18PM
(#48464154)
Yes. That’s possible in addition to using your actual subscription. I’ve been using it via cliproxy for all harnesses and even my own code review agent hooked up to github apps. Not banned yet but I also dont do crazy stuff with openclaw or hermes
Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by smallerize on Saturday June 06, 2026 @06:13AM
(#48423364)
If you're looking for an efficiency-focused harness, I had a pretty good time using the Dirac agent. The line-based anchors were slightly buggy though (this was a couple months ago) and would sometimes add the same line of code multiple times or leave an anchor in the output.
Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by GodelNumbering on Thursday June 11, 2026 @01:54PM
(#48493937)
Creator of Dirac here. Came across this too late. The behavior you mentioned happens more commonly in smaller models, rarely in larger/frontier models. The underlying code is clean but the smaller models often make boundary errors (off by one type). Which models did you observe this with?
Re:Show HN: Lowfat – pluggable CLI filter that saved 91.8% o...
by smallerize on Thursday June 11, 2026 @02:05PM
(#48494126)
That tracks, this was a quantized version of GLM 4.7 Flash. I was surprised because I though this specific thing was not supposed to happen lol.
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.