Yes it is and best price/perf because of the best false positive rate in the biz
But Opus 5.5 medium is incredibly good for reviews as well.
arena.liebig.gg/
@thsottiaux if we could get the amazing chat/app transcription/dictation into codex-cli
that would be a huge unlock
idk what you guys do with it but it feels so incredible in the chat and I wish I could use that in cli (i do not want to use live mode, notably)
This is pretty cool tbh.
First, huge ffmpeg fan here, goated software.
Second, actually very ethical approach.
Not many people truly understand each codec to the level necessary to send one liners fired from the hip so being very cautious makes sense. Gg
Had the exact same issue. Tried to use it for my personal account, reused my phone number I used for a different business (duh, I have one phone guys) - banned and zero way to talk to a human
Infuriating.
It makes me stupidly happy that this is exactly the issue I ran into with my review suite plugin months ago
I was pretty proud of my little circuit breaker (incidentally also after 3 rounds) and seeing it validated makes me very happy
Cap your agent review loops at 3 rounds
Per their writeup, one Claude Code PR ran 50+ rounds of review and fixes overnight, mostly re-flagging old code. After the cap, PRs needing 5+ rounds went from 8.9% to 1.5%
for your REVIEW.md
After 3 rounds, stop and ask the author to rethink the approach
xitter.cf/ClaudeDevs/status/2111…
Get this to the Ordnungsamt and Verbraucherzentrale asap.
This is fraud.
And recent legislation is cracking down hard on funky landlords
I refuse to call any model even remotely AGI until models can actually remove things.
Comments that are referring to old, legacy state with zero reason (worst offender imo).
Code that should have never existed.
Tests that are tautologies.
UI copy with "not xyz".
I'm not putting my card down for a free trial (the word free means something) if my company would be worth 200m
If you offer a trial you offer a trial.
Let your product speak, why do you need to scam attention span issues?
Even for reviews, Opus (medium) is now actually useful and good.
While 6.1-Sol-med/xh is still my cost x time x perf recommendation (cause very few false flags), you don't require GPT models anymore for reviews.
Truly wild.
arena.liebig.gg if you want to play around