On: GPT-6 Sol and Luna

[yipinwong]

I've been raving about Luna 5.6 as it's dirt cheap, and "intelligent enough". Double quoted.

Now GPT 6 Luna is even cheaper, and more intelligent, there is no going back... to SOL 5.6 for intelligent layer.

[dmazin → yipinwong]

Per the benchmarks in the post, Luna 6 is at best a couple points superior to Luna 5.6 and (unless I’m reading it wrong) xhigh has actually degraded in quality?

I was hoping for a serious Luna upgrade. It was already cheap enough. This feels more like a price reduction than an upgrade.

That said, if the new Luna is able to handle ultra mode and subagents v2 in codex cli, then at least that’s a win.

[yipinwong → dmazin]

Benchmark doesn't really show the whole story.

I forgot which model degraded in quality as time went by, but let's try out Luna 6 for a few more days to confirm for upgradability.

[tripledry → yipinwong]

> Benchmark doesn't really show the whole story.

For me it seems like benchmarks are mostly noise, and the rest is based on vibes. Some find newer models annoying, some are amazed.

[elcritch → yipinwong]

If you put Luna on Max it's still cheaper than Sol, but can achieve similar results. Though slower and with more iterations. Still it barely nudges my subscription usage!

[yipinwong → elcritch]

ty for the suggestion. I really never used "max/ultra" on Luna, and will give it a try.

[wartywhoa23 → yipinwong]

Ah, the ravers are not what they used to be anymore...

[yipinwong → wartywhoa23]

Price is a big selling point for a normie like me.