FM Speaker Highlight: @bnl5110 A founder who designs new ways for humans to interact — blending play, architecture, and technology to build tools and communities that feel both experimental and deeply human. She is the founder of Loopy, a tool for animating realities with over 50 million organic impressions, and previously designed new interactions at Y Combinator Research. Really excited to have her joining us at FM26. FUTUREMODE 2026 📍 Taipei Expo Dome | Sep 4–6, 2026 🌐 🏟 Early Bird Till 7/1 Local - International -

🔥 RAPBEAT 2026 Final Lineup Officially Announced! ✨ New surprise additions including The Cohort, H1GHR MUSIC, NCT TAEYONG, Loopy, Shyboii, Wuuslime, Marv, Rich Iggy, GGM Kimbo — and more! 🎤 Diverse flows clash freely, hard-hitting beats strike straight to the soul, melodic rap warms the entire venue. Come embrace an ultimate hip-hop feast for all rap fans! 📍 Seoul | Oil Tank Culture Park 📅 6.20 & 6.21 🎫 Available Ticket Tiers · ROCKET PASS (1 DAY – SAT / SUN) · 3RD TICKET (1 DAY – SAT) · 4TH TICKET (1 DAY – SUN) 👉 Click secure your limited spot now. The full final lineup is assembled. Let’s enjoy the purest hip-hop carnival together! #RAPBEAT2026# #RAPBEAT# #MusicFestival# #RAPBEATFESTIVAL# #rap# #HipHop# #ZICO# #JayPark# #LNGSHOT# #RIIZE# #Wuuslime# #Marv# #Loopy# #YangHongWon# #TAEYONG#

MADLY MEDLEY 2026 is officially announced! 🔥 The first round lineup is already heating up! ✨ AKMU, MONSTA X, IMJM with Swings, The Rose, Tiger JK & yoonmirae, BIBI, Paul KIM, LOOPY… More artists to be announced soon! 📍 Seoul | OIL TANK CULTURE PARK 📅 September 5~6, 2026 ⏰️First-Round Ticket Sales: July 9, 2026, 18:00（UTC+9） 🎫 First-Round Ticket Options: - 1ST TICKET (1DAY-SAT) - 1ST TICKET (1DAY-SUN) One stage, a thousand rhythms. Madly Medley—where all sounds come together💫 Click to secure your tickets in advance! #madlymedley# #musicfestival# #Yedong# #monstax# #swings# #BIBI# #loopy#

Looped transformers are a popular architecture topic right now. This new technical report extends the loop across tokens. Recurrent Looped Transformer (RLT) makes the decoder recurrent over every token, prompt and response included. A causal encoder builds global KV memory. For each new token, the decoder combines the token's encoder representation with its own final hidden state from the previous token and a sliding-window cache of recent activations. With a 48-layer decoder, the computation path after t tokens runs through 48t decoder blocks, while each token still executes a fixed number of blocks. Depth grows with the sequence and per-token cost stays the same. The same state transition is used for pretraining, SFT, sampling and RL replay, and nothing resets at the prompt-response boundary. RL replay rebuilds states under the current weights instead of reusing stale rollout states. The report is a design proposal. The author states that reasoning gains, hardware speedups and RL scaling are goals that have not been measured yet. Paper: Chat with Paper:

Loop is now so good at detecting patterns that we're using it to optimize Brainstore. We pipe all of our query plans into Braintrust and found a bunch of low-level optimizations, eg a spot in our regex code where we were over-fetching duplicate ranges from object storage.

Loop engineering has emerged as a new skill for AI engineers But there is very little research measuring how effective it is. The best results on full tasks in a new benchmark is ~25%. LoopArena from AMAP evaluates the outer loop rather than the coding agent. A Controller model receives a structured summary after each round and instructs a separate fixed Worker agent on what to do or verify next, or decides to stop. Holding the Worker constant makes the result readable, since an end-to-end run cannot tell you whether success came from the guidance or from the agent carrying it out. The named failure modes will be familiar to anyone running long agent sessions: - Trusting a stale progress note - Skipping needed verification - Spending budget in the wrong direction - Stopping before the task is safe to submit Paper: Chat with Paper: