Register and share your invite link to earn from video plays and referrals.

Search results for haikyu
haikyu community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including haikyu
OFFICIAL TRAILER ~Fukurodani VS Mujinazaka~ HAIKYU!!: “The Place Where Monsters Go” special anime! Scheduled for TV broadcast in 2027! #ハイキュー# #hq_anime#
0
367
76.8K
27.2K
Forward to community
Unstoppable on the court and unbeatable in charm! Atsumu and Osamu Miya have joined the Qset+ line, ready to outplay the competition and look absolutely cute doing it. Preorder now at GOODSMILE ONLINE SHOP US! Shop: #Haikyu# #Goodsmile#
Show more
Anthropic RL-trained Claude Haiku 4.5 to be an alignment auditor inside Petri, their production auditing scaffold. Training Alignment Auditors via Reinforcement Learning Paper:
Show more
"Make a haiku based on my X account" Pranks on the regime Phone in hand, laughter erupts Total Victory
First to create a haiku about my pussy gets a DM
0
122
12K
1.5K
Forward to community
🖥 A mere 9B open model rivals Claude Haiku 4.5 on terminal-use benchmarks. And the data, models, and code are all open. Title: Tmax: A simple recipe for terminal agents URL: An Ai2/UW work that gives terminal-agent RL training a simple, reproducible recipe. Here are the 3 standout points. 🧩 A compositional data generation pipeline Tasks are synthesized at scale from the product of 9 axes (domain, skills, verifier, persona, difficulty, and more), with Gemini-3-Pro generating the Dockerfile and unit tests. Expensive quality validation is skipped; RL just drops pass-rate-0 samples. The result is Tmax-15K, 14,600 environments, over 2.5x larger than prior data, contamination-free and the hardest of the bunch. ⚙️ A simple outcome-only RL recipe The reward is just "did it complete the task." Since naive GRPO collapses in long-horizon agent settings, they stabilize with DPPO (masking divergent logprobs), an FP32 LM head, and a large group size of 32. This recipe lifts Qwen 3.5 9B to 27% on Terminal-Bench 2.0. 📈 Strength, generalization, and full release It improves over the Qwen baseline at every size from 2B to 27B. It also lifts non-terminal evals, SWE-Bench Verified 44 to 53.5 and AIME 73 to 91, and generalizes across harnesses and model families. Data, models, and code are fully open on GitHub. A strong foundation for open terminal-agent research. #TerminalAgents# #ReinforcementLearning#
Show more
[📢] #BABYMONSTER_INFO# 𝐁𝐀𝐁𝐘𝐌𝐎𝐍𝐒𝐓𝐄𝐑 𝐒𝐔𝐌𝐌𝐄𝐑 𝐏𝐎𝐏-𝐔𝐏 𝐒𝐓𝐎𝐑𝐄 𝟐𝟎𝟐𝟓 @ 𝐇𝐀𝐍𝐊𝐘𝐔 𝐁𝐄𝐘𝐎𝐍𝐃 𝐖𝐎𝐑𝐋𝐃 📍LOCATION:Hankyu Department Store Umeda Main Store 3F BEYOND WORLD Event Space1 🕐DATE : 2025.08.13(WED) - 2025.08.19(TUE) ⏳OPERATING HOUR : 10:00~20:00 Come and Visit🧡 🔗POP-UP STORE 🔗GOODS #BABYMONSTER# #베이비몬스터# #ベイビーモンスター# #YG# #SUMMER#
Show more