Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)@teortaxesTex

> We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP Good demonstration that a lot could be squeezed out of "mere" DSA on benchmarks, too.

152 likes8 repliesPosted Jun 16, 2026

Remix this post

Your note

Private to you, and used when you remix this post.

Viral score

Based on absolute engagement — the platform doesn’t expose follower counts here, so large accounts score higher.

From likes, comments.

Why it worked

Uses concrete numbers instead of vague claims, which makes it credible and quotable.
Follows a clear Hook → Context → Landing shape, so the reader always knows where they are.
Ends on a short line that is easy to quote and repeat.
Written from experience rather than as advice, which is harder to argue with.
Short enough to read in full without expanding, which removes a step before the point lands.
Quotes someone directly, which makes the moment concrete rather than summarised.

The mechanics

Hook: Plain observation
Structure: Hook → Context → Landing
Style: Conversational paragraphs at a steady pace.
Tone: concrete, corporate
Mechanisms: Specificity
Written for: People building with AI

Analysis by ViralLoop — not written by the original author.

Post by Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) on X