#reasoningmodels
Live, measured metrics for the hashtag #reasoningmodels from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.
Own #reasoningmodels
This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.
Day-by-day usage
measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-28 03:32 UTC0 uses by 0 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.
Related hashtags
measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-28 03:32 UTCLive pulse
measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-28 03:32 UTCEverything below is measured over the latest 31 public posts (spanning ~13887 hours).
Posting hours (UTC) — busiest: 20:00
Languages: English (29) · Korean (1) · German (1)
Avg boosts / post: 0.4
Top of the latest posts
2025 saw significant advancements in #LLMs, particularly in the areas of #reasoning and #agent based systems. #Reasoningmodels, capable of breaking down #complextasks and utilising tools, revolutionised #coding and #search. The year witness
Apparently AI reasoning models like Deepseek-R1 and OpenAI o1 suffer from "underthinking", where they abandon promising solutions too quickly, leading to inefficient resource use. To address this, a "thought switching penalty" (TIP) was dev
Common assumption: RL beats rejection fine-tuning because it explores more solution paths. New result: RFT explores just as much. RL's edge comes from building compositional reasoning strategies, not coverage. That changes what you should a
Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/reasoningmodels