Gate News message, April 24 — Zhang Chi, a former engineer at ByteDance’s Seed team and current assistant professor at Peking University, revealed on the podcast “Into Asia” that ByteDance requires approximately six months to complete one full cycle of large language model training (pretraining plus post-training), while Google reportedly needs only three months. Zhang attributed the speed difference as a core reason why Chinese companies struggle to catch up in AI development.
Zhang described a “benchmarking culture” within Seed, where team leaders are evaluated based on benchmark scores they oversee, and all members focus on boosting numbers. However, he noted this does not translate into better user experience in practice. While Chinese major companies’ models appear competitive with U.S. frontier models on paper, they fall short in actual usage. Seed’s goal is to reach global top-tier performance, but Zhang stated he does not believe the team has achieved this, nor has it met the domestic leadership target.
In late 2024, Seed considered itself on par with GPT-4o, but following DeepSeek’s release, the team recognized the gap remained. When Zhang joined, the entire group was urgently pivoting toward reinforcement learning to address the shortfall.
Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to
Disclaimer.
Related Articles
Anthropic Rolls Back Claude Code Changes After Quality Decline; All Fixes Complete
Gate News message, April 24 — Anthropic has acknowledged a recent decline in Claude Code quality and confirmed that all related issues have been resolved through rollbacks and fixes. The problems stemmed from three product and prompt adjustments made between early and mid-April.
On March 4, the
GateNews10m ago
NeoSoul Co-Founder Kaelan: AI Industry Should Allow Toys to Exist, Innovation Often Starts as Experimental Products
Gate News message, April 24 — At a recent Hong Kong forum on intelligent encrypted finance, NeoSoul co-founder Kaelan shared insights on evaluating AI projects in the early-stage, rapidly evolving AI industry. Beyond assessing current products, teams must demonstrate the ability to keep pace with un
GateNews37m ago
Meta and Amazon Agree on Multi-Billion Dollar Deal to Supply Graviton Chips for AI Development
Gate News message, April 24 — Meta Platforms and Amazon Web Services (AWS) have reached a multi-billion dollar agreement to support Meta's artificial intelligence initiatives over the coming years, according to the Wall Street Journal. Under the deal, Meta will use tens of millions of AWS Graviton c
GateNews49m ago
DeepSeek V4-Flash goes live on Ollama Cloud, US-hosted: Claude Code, OpenClaw one-click integration
Ollama Cloud has launched DeepSeek V4-Flash, with inference hosted on U.S. servers, providing three sets of one-click commands to connect Claude Code, OpenClaw, and Hermes. V4-Flash/V4-Pro use a MoE architecture, with native support for 1M context, and reduce costs with Token-wise compression + DSA sparse attention. In a 1M scenario, token FLOPs per token drop by 27%, and KV cache drops by 10%. API-compatible with OpenAI ChatCompletions and Anthropic, making it easy to switch between multiple workflows and lowering costs and data-sovereignty risk.
ChainNewsAbmedia2h ago
Web3 AI Infrastructure AIW3 Raises $2M in Seed Funding Led by Buffalo Capital
Gate News message, April 24 — Web3 AI infrastructure platform AIW3 announced the completion of a $2 million seed round funding. The round was led by Buffalo Capital, with GalaXin Capital and Three-stones Ventures participating as co-investors.
AIW3 is transitioning toward an Agent-as-a-Service
GateNews2h ago
Cohere Acquires German AI Firm Aleph Alpha, Secures $600M Investment for European Expansion
Gate News message, April 24 — Canadian AI company Cohere announced plans to acquire German AI firm Aleph Alpha to strengthen its presence in Europe. Schwarz Group, a backer of Aleph Alpha, plans to invest $600 million in Cohere's Series E funding round.
The funding round is expected to close in 202
GateNews3h ago
