Best part: GPT-5.5 does all of this while being ~3x more token efficient than Opus 4.8. 47k output tokens vs 136k. Oh, it's also cheaper and faster: $6.61/task vs $12.58, 21 min vs 43 min. Enjoy!
@reach_vb
-
GPT-5.5 beats Claude Opus 4.8 on DeepSWE with faster, cheaper performance
By
–
GPT-5.5 is #1 on DeepSWE, a hard long-horizon coding benchmark 70% pass@1 vs 58% for Claude Opus 4.8. And GPT-5.5 gets there with:
~2x faster runs
~1/2 the cost
~1/3 the output tokens Literally, better intelligence per dollar, per minute, per task. -
Reviewing Codex output after 16 hours straight work
By
–
me reviewing codex’s output after it worked for 16 hours straight
-
Using AI Agents for Code Orchestration and Workflows
By
–
this! codex can create and interact with threads across projects and tasks – all you need to do is ask
— Vaibhav (VB) Srivastav (@reach_vb) 29 mai 2026
I’ve used this recently orchestrate multiple worktrees and implement a feature with different PoVs using subagents
and ofcourse to archive, unarchive and find relevant threads… https://t.co/LmIKytkCz6this! codex can create and interact with threads across projects and tasks – all you need to do is ask I’ve used this recently orchestrate multiple worktrees and implement a feature with different PoVs using subagents and ofcourse to archive, unarchive and find relevant threads
-
AI Agent Autonomously Automates PR Merge Workflow
By
–
While working on openai/codex today, Codex surprised me by setting up its own heartbeat automation to poll my PR until CI was green and approvals were in. It kept checking every 10 minutes for an hour, merged the PR once everything was ready, then removed the automation. High
-
Automating work and life admin with Codex scripts
By
–
have had tons of of fun automating boring parts of my job and life admin the past few days with codex and one off scripts oh and no you really don’t need a Mac mini to for this 🙂
-
Identifying Workflows for AI Skills and Subagents
By
–
Copy and paste this into your codex: “Look through my recent Codex sessions and identify repeated workflows or repeated asks. For anything I keep doing manually, suggest:
1. a skill if it is a reusable workflow
2. a custom subagent if it is a bounded role or investigation task -
GPT-5 Model Selection and Cost Optimization Strategy
By
–
Unironically, I do think they’d be atleast ~40% cheaper if they used GPT 5.4/ 5.3-Codex w/ Codex harness Lots depend on model, harness, caching and compaction – and how you use it for your use-case Happy to cover the next month in the name of science! 🙂
-
Codex: Turning Repeated Prompts into Reusable AI Skills
By
–
Codex Tip: ask Codex to look through your past sessions and turn repeated prompts into reusable skills + subagents you’ll probably find the same stuff showing up again and again: “check why CI failed”
“review this PR”
“write the changelog”
“trace this bug”
“clean up this diff” -
GPT-5.5 Generates 30k Lines QML with Agentic Reasoning
By
–
GPT-5.5 cranking out 30k lines of QML for the Omarchy 4 branch + nailing subtle agentic reasoning!!