Eianun
529 posts
Eianun
@Eianunbits
电商毕业1年｜大二自学Midjourney+SD创业单月赚10w+第一桶金 自学编程・Linux・AI深度学习・Agent｜ Web3（偶尔撸毛） & AI工具探索者｜ U卡 & eSIM收集控｜
Beigetreten Ağustos 2022
489 Folgt437 Follower
【Codexの賢い使い方】
- Terra Ultra級の性能が必要でない限り、Luna XHigh /Maxを使用
- Sol High未満は使わず、LunaのXHigh/Maxを使用
- Sol XHighは使わず、代わりにTerra Maxを使う
- 最重要課題のみSol Maxを使う
要するにLuna XHigh/Max,Terra Max,Sol Maxだけでいい
Sebastian Raschka@rasbt
Sorry, there's been a label shift in the original plot I made above. The corrected plot is below. I.e., Ultra = Max and so on. The relative comparisons between models is still correct. (Afaik Ultra runs Max with 4 subagents mainly for speedups) The numbers come from the Artificial Analysis Coding Agent Index as mentioned in the chart. And here's the source link: artificialanalysis.ai/agents/coding-…
日本語
🚨 New GPT-5.7/GPT-6 leak just surfaced
OpenAI appears to be prepping the next major leap:
• Targeting release in August
• 1.5M+ context window
• Brand new pre-train foundation beyond the old base, rumours of 10T scale
• Expected substantial agentic/reasoning gains to compete with Mythos/Fable tier and improve upon sol.
Are you looking forward to this model being released?
English
Try Grok 4.5 and see for yourself
Min Choi@minchoi
Ok Grok 4.5 is insane. People are already building things that shouldn't be possible this fast. 10 wild examples:
English
A correction after robust testing.
Replace GPT 5.6 Terra (High) with GPT 5.6 Luna (Extra High) for execution.
Same performance but:
> 1.3x faster than Terra
> 2.5x cheaper than Terra
In Codex, you burn 2.5x less limits if you use GPT 5.6 Luna (Extra High) as subagents.
CJ Zafir@cjzafir
English
SuperGrok is super useless now. Every feature, that is not basic chat, makes it less usable with each request. Definitely will not be putting more money into this product.
English