AI NewsCursor

GLM 5.3 and its faster sibling, GLM 5.3 Flash, are now selectable inside Cursor. Open weights means anyone can download and run the model themselves, unlike closed models from OpenAI or Anthropic.
Cursor added GLM 5.3 and GLM 5.3 Flash from Chinese lab Z.ai on October 1. On Cursor's own CursorBench 4.0 chart, GLM 5.3 Max is the best-scoring open-weight model, landing near Sonnet 5.5 and Astra on the quality-versus-cost curve, though still a step behind the top closed models.
Developers have been asking Cursor to add GLM for weeks, since open models often cost far less to run than proprietary ones. GLM 5.3 ships under the permissive MIT license, with a 1 million-token context window.
Key Capabilities:

• Open weights: Free to download, run locally, or host yourself.
• Long context: Supports up to 1 million tokens, roughly 750,000 words, in one conversation.
• Three effort levels: Low, High, and Max reasoning modes, with High as the default.

[9:45 AM]

The new /visualize command lets developers generate charts and diagrams inline while chatting with a coding agent, without leaving the interface.
Cursor released /visualize for its Agents Window, letting users point an agent at a file, query, or log and get a rendered chart or diagram back in the chat. It builds on Cursor's earlier Canvas feature, which let agents create dashboards with reusable chart and table components.
The command needs no separate setup or added cost. Developers say it's useful for quickly checking a metric or sketching a system diagram mid-conversation, rather than switching to another tool.
Key Capabilities:

• No setup: Works immediately in the Agents Window for all Cursor users.
• Multiple sources: Can visualize data from files, queries, logs, or connected tools.
• Builds on Canvas: Uses the same React-based chart and diagram components as Cursor's Canvas feature.

Cursor reduced token costs by 7% with no drop in agent quality, through tighter prompts, selective tool loading, better caching, and reading fewer line numbers when scanning files.
Cursor announced on September 23 that changes across its agent harness cut token costs by 7% with no drop in agent quality. The system prompt and tool definitions, sent every turn, were among the biggest controllable costs, so tightening them cut cold cache misses by 20%.
Another fix targeted file reads: instead of numbering every line, the agent now numbers only every tenth, still enough to cite code accurately, cutting cache-read tokens by 1.6%. Longer agent runs also delegate more work to subagents that start with fresh context windows.
Key Capabilities:

• Trimmed context: Tighter system prompts and selective tool loading cut cold cache misses by 20%.
• Smarter file reads: Numbering only every tenth line cut cache-read tokens by 1.6%.
• No quality trade-off: All changes were validated to preserve agent output quality.