Hacker News new | ask | show | jobs
by mainmailman 1 day ago
Do you really think they mean they’ve been using mythos
2 comments
user43928 1 day ago
In my mind there are three tiers:

The SOTA: Fable, GPT 5.6 Sol, Opus 5

The "enterprise admin did not turn on the new models": Opus 4.8, GPT 5.5

The "I love hallucinated garbage": Sonnet, Qwen 3.6, GPT 5.4 mini, GPT 5.3 Codex, etc.

Results vary widely

link
inigyou 1 day ago
What did your tiers consist of when GPT 5.3 was the latest?
link
user43928 1 day ago
I believe I was still using Opus 4.6 with the Claude Code CLI.

Before that, Gemini 3 Pro in Antigravity.

I have no experience with GPT 5.3 beyond seeing the nightmares colleagues produced in their MRs with GPT 5.3 Codex. It could be that they had the distilled 5.3 Codex Spark selected, I am not sure.

link
cubefox 1 day ago
Obviously no. There is also a significant capability difference e.g. between Opus 4.8 and Fable.
link