Using Claude Code can dramatically change your view of AI
matt_slotnick · x · 2026-07-20
Switching work from Claude to **Claude Code** can be a big eye-opener for what AI can actually do. The author argues that many people underestimate model capability simply because they have never used it in a real coding workflow. The same point applies to moving from ChatGPT to **Codex**: hands-on use can sharply change your perception of the slope of AI progress and current capability.
More from coding & agent
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21
- X post asks whether Cursor Composer, built on Kimi models, would also be banned — max_paperclips · 2026-07-21
- A developer’s Codex usage is draining pooled enterprise credits at a small company — Distinct_Relation_62 · 2026-07-21