have you given codex a shot? would be interested in your feedback on how we can make it better. in the past couple weeks we've added roughly made inference ~60% faster across the board in codex!
@reach_vb
-
Developers Praise OpenAI’s Codex for Efficiency
By
–
"Developers Praise OpenAI's Codex for Limit-Busting Efficiency" gm
-
Using LLMs to generate their own technical documentation
By
–
yeah but also for every model release I ask the model itself to write its doc, it’s a nice way to attribute the release to the model imho
-
Comparing AI model speed and utility for coding and automation
By
–
capability wise it’s definitely not at par with 5.3-codex but the faster speed definitely helps with a lot of knowledge work, automations and debugging
-
Discussion on LLM inference tokens per second
By
–
can you feel more than 1000s of tokens per second, anon!? ✨
— Vaibhav (VB) Srivastav (@reach_vb) 12 février 2026
codex -m gpt-5.3-codex-spark pic.twitter.com/6UJzWE6qqjcan you feel more than 1000s of tokens per second, anon!? codex -m gpt-5.3-codex-spark
-
OpenAI releases new instant model, Deep Research, and API enhancements
By
–
wdym? we released a new instant model, 5.2 Deep Research, hosted shell, skills and compaction in the API – all of this in just the last 5 days! there’s never been a better time to build w/ OpenAI
-
Recommendation for using Codex for long-running coding tasks
By
–
for long running tasks I’d really recommend using codex since it’s purpose built for that task
-
Integrating Agent Skills with OpenAI Responses API
By
–
Developers! You can now use Agent Skills directly with the OpenAI Responses API You can create a workflow in 2 simple steps:
1. Bundle the SKILL md + scripts + assets 2. Upload the bundle and mount into the shell tool That's it! The model can discover it and execute code -
User experience comparing Codex 5.2 and 5.3 in plan mode
By
–
anecdotally I’ve enjoyed the /plan mode w/ 5.3 codex quite a bit. long shot, but do you have a sample prompt where you enjoyed 5.2 over 5.3? (DMs open)
-
Community reproduction confirms GPT-5.3-Codex token efficiency
By
–
nice to see community repro of how token efficient GPT-5.3-Codex is! and we’re only getting started