Claude Code provides clearer intermediate summaries than Codex.
Biggest difference between Codex vs Claude Code: Codex won't stop working towards a /goal. CC quits on hard tasks and needs encouragement to keep going. So weird.
BUT Codex is pretty bad at intermediate summaries. Its outputs read like esoteric CoT summaries. CC wins on HCI.
Something weird I've also noticed: Claude having a soul.md and an actual personality, while frequently attempting to convince me that what I am trying to do can't happen, makes me hesitate pushing it to try harder when it quits on a goal.
NEVER felt that hesitation with Codex.
Biggest difference between Codex vs Claude Code: Codex won't stop working towards a /goal. CC quits on hard tasks and needs encouragement to keep going. So weird.
BUT Codex is pretty bad at intermediate summaries. Its outputs read like esoteric CoT summaries. CC wins on HCI.
Claude Code provides clearer intermediate summaries than Codex.
Biggest difference between Codex vs Claude Code: Codex won't stop working towards a /goal. CC quits on hard tasks and needs encouragement to keep going. So weird.
BUT Codex is pretty bad at intermediate summaries. Its outputs read like esoteric CoT summaries. CC wins on HCI.
Users in the replies are frustrated with Claude quitting or negotiating down on hard coding tasks, calling the refusals a new and worsening problem that requires constant hand-holding.
