Golem (GLM) Plunge

Chinese tech giants like ByteDance, Alibaba, and Tencent are accelerating the rollout of integrated AI model subscription services—dubbed “model supermarkets”—to provide developers with bundled access to multiple leading domestic large language models (LLMs). ByteDance’s Volcengine recently upgraded its "Coding Plan" by adding newer models like GLM-5.1, Minimax M2.7, and Kimi k2.6, allowing subscribers to use various top models under a single monthly fee starting at ¥40. However, user feedback reveals significant issues, including rapid consumption of usage limits (e.g., hitting caps within hours), frequent server errors (like HTTP 429), and slow response times during peak hours. Complaints about misleading deduction rates—where calls to advanced models consume more quota—are also common. The trend is industry-wide: Alibaba, Tencent, and Baidu have all launched similar multi-model coding plans. While these platforms reduce trial costs for developers, they also expose challenges in balancing affordability with service quality and computational stability. Amid this shift, independent AI companies like Zhipu, MiniMax, and Moonlight Face (Kimi) are developing strategies to avoid becoming mere “pipes” in this ecosystem—focusing on vertical applications, autonomous agents, and long-context models to retain competitiveness. Analysts suggest that, while platform aggregation may pressure model firms in the short term, specialized and vertical AI capabilities will remain differentiated in the long run.

Zhipu AI, a Chinese AI company, has reached a market capitalization exceeding HK$1 trillion, with its stock rising over 1900% this year. Its valuation now rivals half of Alibaba's, highlighting intense market speculation around Chinese AI firms. Despite 2025 revenues of only ¥7.24 billion and a net loss of ¥47.18 billion, investors are pricing in massive future growth, driven by its GLM-5.2 model and its positioning as China's potential answer to Anthropic. The surge reflects a broader trend: soaring valuations for AI companies across primary and secondary markets. DeepSeek's latest funding round valued it over $50 billion, while other players like MiniMax and StepFun are also targeting listings. This capital influx is concentrated in hard tech and AI within Hong Kong's IPO market. However, concerns about a bubble are mounting. Zhipu's high valuation, volatile trading, and impending share lock-up expiries pose near-term risks. The core challenge for Zhipu and its peers is transforming advanced model capabilities into sustainable revenue and profit, following the path of Anthropic which is nearing operational profitability. The trillion-HK dollar mark for Zhipu represents a symbolic peak for China's AI industry, but its permanence hinges on demonstrable commercial success.

Free, Open-Source Alternative to Claude Science: OpenScience Lets Researchers Use Any AI Model Like DeepSeek or GLM Shortly after Anthropic launched Claude Science, a specialized AI workbench for scientific research, the open-source community responded with its own solution: OpenScience. Developed by YC-backed Synthetic Sciences, this platform offers a full AI research workflow covering literature review, hypothesis generation, code experimentation, and paper writing. Unlike Claude Science, which is restricted to macOS/Linux, paid users, and only Claude models, OpenScience is model-agnostic and free. Researchers can use any AI model—DeepSeek, GLM, Claude, GPT, or local models via Ollama—simply by providing their own API keys, keeping data private. OpenScience features over 250 editable research skill packs, more than four times Claude Science's initial offering, and supports one-command installation. It emphasizes openness, arguing that scientific AI tools should not be controlled by a single company. The project includes a clear disclaimer of no affiliation with Anthropic, reflecting caution in the open-source community.