@digitalocean See more details here digitalocean.com/open-source
English
Peter Dave Hello͌ͯͦ̉
4K posts
Peter Dave Hello͌ͯͦ̉
@PeterDaveHello
Free and open source software enthusiast, Maintainer and active contributor of few projects.
Taiwan, R.O.C Bergabung Aralık 2014
2.7K Mengikuti709 Pengikut
🎉 Thrilled to be sponsored by DigitalOcean 🐳 through their OSS program! Their credits are powering 🚀 the maintenance of my open source projects:
• github.com/PeterDaveHello…
• github.com/PeterDaveHello…
Thank you @DigitalOcean for supporting open source! 💙🌊🐳
#DOForOpenSource
English
@PeterDaveHello Or this x.com/glwillen/statu…
Gabe@glwillen
Been experimenting with async auto-compaction with uninterrupted compaction in Codex. Context compacts in the background while the agent keeps running. No pauses. No losing the turn. No broken tool calls. Long sessions stay smooth. Should I open a PR? 👀 @thsottiaux @OpenAICodexCli @OpenAIDevs
English
I definitely need a "/compact-fast" command in the Codex CLI.
It takes me more than 10 minutes to get a single line:
• Context compacted
🤪🤪🤪
English
My `npx slopmeter@latest --all --dark`✍️
22B input and 210M Tokens input and output.
Including Claude Code, Codex, and Open Code.
Not supported GitHub Copilot, Roo Code, Cline, and Kilo Code usage is not included yet.
What's yours?
Jean P.D. Meijer ― 🇪🇺 eu/acc@initjean
create one for your fav coding agent, run: npx slopmeter@latest --codex npx slopmeter@latest --claude npx slopmeter@latest --opencode jthe repo is now on github github.com/JeanMeijer/slo…
English
Codex got more speed.
With /fast mode, GPT-5.4 runs 1.5x faster with the same intelligence and reasoning.
Move through coding tasks, iteration, and debugging while staying in flow.
English
@kevinkern I only need to cost 2x 🤣🤣
x.com/PeterDaveHello…
Peter Dave Hello͌ͯͦ̉@PeterDaveHello
/fast toggle Fast mode to enable fastest inference at 2X plan usage
English
gpt 5.4 and fast mode at 3x plan usage in codex 0.110
fm needs to be enabled in codex settings under
[features]
fast_mode = true
English
/fast toggle Fast mode to enable fastest inference at 2X plan usage
English
@OpenAIDevs Released in v0.111.0, nice!
x.com/PeterDaveHello…
Peter Dave Hello͌ͯͦ̉@PeterDaveHello
GPT-5.4 Fast with Codex CLI v0.111.0⚡️
English
@GHchangelog We do need more Copilot insights for org owners!
English
Org-level Copilot usage metrics dashboard now available.
github.blog/changelog/2026…
English
📊Noticeable improvements with @OpenAI’s GPT-5.2-Chat-Latest vs GPT-5.2 (#5 vs #29 Overall)
Where GPT-5.2-Chat-Latest gains:
Text:
- Coding (+13: #6 vs #19)
- Hard Prompts (+21: #4 vs #25)
- Instruction Following (+21: #7 vs #28)
- Longer Query (+10: #14 vs #24)
- English (+33: #7 vs #40)
Occupational:
- Software & IT Services (+19: #5 vs #24)
- Writing, Literature, & Language (+9: #20 vs #29)
(note: rankings calculated with style control)
Arena.ai@arena
GPT-5.2-chat-latest, the newest model powering ChatGPT, is now in the Text Arena top 5! Highlights: ▪️Top 5 scoring 1478 on par with Gemini-3-Pro ▪️+40pt improvement over the GPT-5.2 model ▪️Top in key categories: Multi-Turn, Instruction-Following, Hard Prompts, Coding A strong step forward for @OpenAI and a highly competitive return to the top of the leaderboard.
English
@PeterDaveHello congrats man love to see how you stayed consistent with open source for twelve years.
English
My 12-year journey on GitHub ✨
Mostly small contributions to projects I use or will use, but every tiny step counts 🎉
English
github.com/openai/codex
A reminder that Codex CLI has been open source since day 1.
English