Trans MTF/gender-fluid. Privacy & security enthusiast, into cyber security and utilizing AI in unique ways.
- Tweets 176
- Following 1,056
- Followers 150
- Likes 100
Pinned Tweet
Doing this now and it's crazy how differently 5.6 Sol acts under a different harness.
If you aren't yet bold enough to install the Codex app, you can stay in the presence of your orange crab and point it at GPT 5.6 Sol. Takes 5 minutes. Kudos to Theo for explaining one of the ways to get this done.
Step 1: Install CLIProxyAPI
Step 2: Connect
Step 3: Define following alias and enjoy claudex
```
alias claudex='CLAUDE_CODE_SUBAGENT_MODEL=gpt-5.6-sol \
CLAUDE_CODE_ALWAYS_ENABLE_EFFORT=1 \
CLAUDE_CODE_MAX_TOOL_USE_CONCURRENCY=3 \
ENABLE_TOOL_SEARCH=false \
claude --model gpt-5.6-sol'
```
If this gets blocked, I owe you a reset.
38
Daybreak Blue 👀, I haven't seen anybody post about this yet... This is the first time that I see a cyber security model that I can select via the model picker
@theo @WesRoth @bijanbowen @RayFernando1337 @AlexFinn @rileybrown
1
2
623
I’m physically disabled, and Codex announced real-time voice.
I figured out an unsupported and hidden way for anyone to get ChatGPT real-time voice on the desktop app.
The clue? A glowing orb appeared for 1 second—then vanished.
Guide + helper:
orb-blinked-once.clockworkhr…
1
69
STEP 7 — Press:
Control + Option + Command + V
The voice orb should stay open.
Afterward, quit ChatGPT to clear the one-session workaround.
The guide includes the exact Terminal check for confirming the inspector is closed.
1
11
The result:
START: 00:58:44.874Z
STOP: 01:00:56.346Z
A real 2m 11s voice session.
This is unofficial, version-specific, and may break after an update. Staged rollouts exist for operational reasons.
Full guide + helper:
orb-blinked-once.clockworkhr…
11
Josh (Scarlett) ♿️ 🏳️⚧️ retweeted
Meet kbd-1.0-codex-micro, built with @work_louder.
Map the buttons and joystick to your workflow, and keep your pinned chats in view.
Get yours before stock returns 410.
1,045
833
9,478
4,873,524
Been encountering this issue frequently today with all GPT 5.6 models attempting tasks or goals exceeding 20 minutes. It consistently reports being at capacity, leaving me puzzled as I perceive that I've reached 96% usage. @thsottiaux, could this possibly be a bug?
1
1
267