Same prompt tested with Step-5-preview.
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
Same prompt tested with Step-5-preview. It's working but the entire design is a messy. Inferior to deepseek-v4.1-flash result. Same settings as before: - single shot - direct api call, no harness
Posted by AJ (7.6k followers) 2 h ago · 7 likes · 571 views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- I am going to Release this for some of you to run today... GLM 5.3 Flash is FASTER than… — @Tech2Wild
- We now have a fixed date for Anthropic's next frontier model. — @vikktorrrre
- what is also crazy is that they jump from Opus 5 to Opus 5.5 right away — @LexnLin
- So happy to see Ethan enjoying the game I built for him. — @ai_for_success
- Qwen 3.8 Flash Next's knowledge cut-off seems to be mid-2025. — @wtogami
- Claude Opus 5.5 Leaks — @vikktorrrre
- Claude Opus 5.5 will outperform OpenAI's GPT-6 Astra👀 — @0x0SojalSec
- Apparently we are getting Opus 5.5 on Tuesday — @LexnLin
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 34.6k posts from 4.9k X accounts over the last 14 days, 1.5k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 15:54 UTC. Full method.