Here is my résumé when it comes to using #GLM 5.1 for refactoring a large #php #laravel code based on #sonarqube warnings/errors:
A DISASTER ‼️ - #claude on the other hand: one shot, everything works.
For the record:
GLM5.1 was running via opencode go. (same prompt) 😞 😢
i don’t think GLM is bad in general. i am talking here about refactoring a large codebase in particular. writing new code or doing small stuff works fine.
🧵 👇
[Перевод] Локальный запуск GLM-5.1
Перевод подготовил автор канала Друг Опенсурса , приятного прочтения, заранее благодарю за подписку В этой статье мы подробно разберем процесс развертывания GLM-5.1 с использованием llama.cpp и форматов GGUF. Узнаем о системных требованиях, сборке и настройках, оптимизации и практическом применении.
https://habr.com/ru/articles/1022242/
#glm51 #llm #Llamacpp #Unsloth #GGUF #Локальный_запуск #tool_calling #Zai #искусственный_интеллект
Z.ai、GLM-5.1を公開：SWE-Bench Pro 58.4と8時間連続実行でエージェンティックコーディングを前面に
Z.aiが公開した新モデル「GLM-5.1」は、いわゆる単発のコード生成を競う段階から、長時間の自律実行でどこまで成果物を出せるかへと、評価軸そのものをずらそうとしている。公式ドキュメントでは、単一タスクを最大8時間にわたって継続し、計画、実行、テスト、修正、最適化までを回し切ることを中核価値として打ち出した。従来の「1ターンでどれだけ賢いか」ではなく、「長い作業をどこまで破綻せずにやり切れるか」を前面に出した構図だ。 同社はGLM-5.1を最新のフラッグシップモデルと位置づけ、コーディング性能はClaude […]
https://winbuzzer.com/2026/04/09/z-ai-releases-glm-5-1-754b-model-tops-swe-bench-pro-xcxwbn/
Z.ai Releases GLM-5.1: 754B Model Tops SWE-Bench Pro
#AI #Zai #GLM51 #GLM5 #AIModels #AgenticAI #OpenSourceAI #AICoding #VibeCoding #ChinaAI #AIBenchmarks #GenerativeAI
GLM-5.1, 600번 반복 끝에 6배 성능을 끌어낸 AI 코딩 모델
Z.ai의 GLM-5.1은 600번 반복으로 6배 성능을 낸 AI 코딩 모델. 오래 실행할수록 나아지는 장기 수평선 능력과 MIT 오픈소스 공개 소식을 소개합니다.
Paul Couvert (@itsPaulAi)
Zai가 새로운 오픈소스 모델을 공개했으며, Opus 4.6과 GPT-5.4에 견줄 만큼 경쟁력이 있고 일부 벤치마크에서는 더 뛰어나다고 한다. 비용도 훨씬 저렴하며 Claude Code나 OpenClaw에서도 사용할 수 있다.
There's no way 🤯 Zai has just released a new open source model which is competitive with Opus 4.6 and GPT-5.4... And even better on some benchmarks! - 5x cheaper than Opus 4.6 - 3x cheaper than GPT-5.4 You can even use it in Claude Code or OpenClaw. Weights and more below
Ability to tackle long context tasks is so important for the most useful of applications for LLMs.
A lot of research involves disproving hypotheses. Aiding researchers by allowing them to set the skeleton for exhaustive search, and then using an LLM as an evolution function has been proven to work (see Alpha Evolve, Shinka Evolve, Darwin-Gödel Machines).
Training this ability to break outside the box through RL of these trajectories, paired with techniques to allow for unbounded input and output context length (RLM) seems to be the key.
Life Japan
michabbb
Habr
Walk News
Japan Pop News
Y Kobayashi
Winbuzzer
AI Sparkup
sayzard
Bogdan Buduroiu