Remember Hindsight? Back in Sept., I covered how a local 20B model went from 39% → 83.6%…
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Remember Hindsight? Back in Sept., I covered how a local 20B model went from 39% → 83.6% on a long-term memory benchmark. Now Hindsight is making the memory system smarter. And it's doing it with tiny specialized models. Hindsight released 3 new open-weight models 👇 🧠 hs-decide-1-flash → 800M parameters 🔎 hs-rerank-1 → 114M 💾 hs-embed-1 → 112M The beauty of Hindsight is that it doesn't ask a large LLM to repeatedly decide if a memory is new or contradictory. Instead, the 800M model makes those decisions directly. No generated paragraphs. One forward pass. Hindsight results are impressiv
Posted by David Hendrickson (12.7k followers) 2 h ago · 24 likes · 962 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Someone tried to remove the dreaded AI writing slop from Qwen3.8-27B. De-slop. — @TeksEdge
- Gemini now has a dedicated developer console for testing custom apps. — @mrfanduu
- Another stealth model 👀 — @ItsmeAjayKV
- Just tried this. I connected the Excalidraw+ MCP to T3 Code through http://Toolport.app… — @btsouth
- Anthropic 把自家做 Claude 应用的示范代码整套放了出来，GitHub 上已经 1.8 万 star。 — @bkdgiffug
- vLLM gave Local AI AMD users something more interesting than another decode speedup. — @TeksEdge
- 28 paid model calls a week just to say "no change." 𝗛𝗲𝗿𝗺𝗲𝘀 Agent skips them. 💸 — @BkashJosi
- Just read @addyosmani's "Critical thinking when agents do the work". Every AI builder… — @Ronny_MiniMax
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 04:17 UTC. Full method.