Hacker News Reader

Been using GLM-4.7 for a couple weeks now. Anecdotally, it’s comparable to sonnet, but requires a little bit more instruction and clarity to get things right. For bigger complex changes I still use anthropic’s family, but for very concise and well defined smaller tasks the price of GLM-4.7 is hard to beat.

View on HN

This aligns very closely with my experience.

When left to its own devices, GLM-4.7 frequently tries to build the world. It's also less capable at figuring out stumbling blocks on its own without spiralling.

For small, well-defined tasks, it's broadly comparable to Sonnet.

Given how incredibly cheap it is, it's useful even as a secondary model.

How is the web search functionality? I have only used deepseek to lower costs from gpt api but had to incorporate a serper to actually do web searches

Assuming you've configured the web search MCP [1], it works well.

[1]: https://docs.z.ai/devpack/mcp/search-mcp-server

Anecdotal, but I've been locked to Sonnet for the past 6-8 months just because they always seem to introduce throttling bugs with Opus where it starts to devour tokens or falls over. Very interested once open models close the gap to about 6 months.

Reply on news.ycombinator.com