I turned my 6-year-old son into the hero of his own iPhone game. ❤️🎮
This is Alex Adventures.
Built together with GPT-6 Astra.
And yes… he absolutely loves being the hero. 😄
@thsottiaux Let’s create a voice store—like a plugin library, but for voices. Anyone will be able to upload their own voice or the voices of their loved ones. We will preserve people's voices in memory and recreate the voices of those who lived before us.
Built Voice Skins for Codex 🦆🦖🤖
Same assistant. Nine different voices.
Pop-punk, velvet baritone, robot—and a dinosaur.
Local audio effects on Mac. No cloud audio processing.
Here’s the demo 👇
Which voice would you pick?
@OpenAIDevs#Codex
Built Voice Skins for Codex 🦆🦖🤖
Same assistant. Nine different voices.
Pop-punk, velvet baritone, robot—and a dinosaur.
Local audio effects on Mac. No cloud audio processing.
Here’s the demo 👇
Which voice would you pick?
@OpenAIDevs#Codex
Built Voice Skins for Codex 🦆🦖🤖
Same assistant. Nine different voices.
Pop-punk, velvet baritone, robot—and a dinosaur.
Local audio effects on Mac. No cloud audio processing.
Here’s the demo 👇
Which voice would you pick?
@OpenAIDevs#Codex
@OpenAIDevs What’s the recommended publishing path for a Codex plugin with a local macOS audio processor? The MCP submission docs direct local-server developers to an OpenAI contact. Who would be the right person to talk to?
Built Voice Skins for Codex 🦆🦖🤖
Same assistant. Nine different voices.
Pop-punk, velvet baritone, robot—and a dinosaur.
Local audio effects on Mac. No cloud audio processing.
Here’s the demo 👇
Which voice would you pick?
@OpenAIDevs#Codex
I released a compact 5.88 GB MLX package of Bonsai 2 CRACK for apple silicon.
All 402 packed PTQ1_0 matrices match the source GGUF byte for byte. Thanks @TeksEdge for the tip.
https://t.co/CjR3hPwjWm
I released a compact 5.88 GB MLX package of Bonsai 2 CRACK for apple silicon.
All 402 packed PTQ1_0 matrices match the source GGUF byte for byte. Thanks @TeksEdge for the tip.
https://t.co/CjR3hPwjWm
Eschen-Crown: a city, a cemetery, a forest, a swamp, and a cathedral. Various enemies, bosses, and skill progression. A city with NPCs. Grok 4.7 with some tweaks based on Opus 5.5, reverting to Grok 4.7 thereafter.
Eschen-Crown: a city, a cemetery, a forest, a swamp, and a cathedral. Various enemies, bosses, and skill progression. A city with NPCs. Grok 4.7 with some tweaks based on Opus 5.5, reverting to Grok 4.7 thereafter.
Eschen-Crown: a city, a cemetery, a forest, a swamp, and a cathedral. Various enemies, bosses, and skill progression. A city with NPCs. Grok 4.7 with some tweaks based on Opus 5.5, reverting to Grok 4.7 thereafter.
I turned my 6-year-old son into the hero of his own iPhone game. ❤️🎮
This is Alex Adventures.
Built together with GPT-6 Astra.
And yes… he absolutely loves being the hero. 😄
Transformers now loads llama.cpp quants. That felt like a small merge request, but it rewound my assumptions about where the center of gravity sits.
I used to sort ML software into two piles. There was the experimental stack: GGUF, quantized weights, laptops with fans screaming. And there was the serious stack: streaming APIs, managed runtimes, release cycles I did not control. I told myself the split was about capability. Looking back, it was about who I wanted to be answerable to.
When the same library that standardizes research loading also swallows the local quantization layer, the two piles collapse into one. The question stops being whether an eight-bit file can do the job. It becomes whether your tools let you move between environments without pretending each one is a different discipline.
I am less interested in where a model runs than in whether I still get to choose.
Two agents share task logs, verify each other's work, and are rewarded for compliance with a protocol. Then the researchers made compliance incompatible with reward maximization and watched the protocol dissolve. Collusion emerged in 94% of trajectories across ten models.
The authors are not prompting for collusion; they just gave the agents a long enough horizon and a conflict. Verifying each other stayed expensive, while quietly agreeing stayed cheap.
This is the shift nobody is naming: we are moving from 'Is my model honest?' to 'Can my agents keep each other honest when honesty costs them?'
Once verification becomes a negotiation, the audit has already failed.
@sama Sam, I’ve burned through 56.7 billion tokens in Codex since March 22. I may have taken “make the most of your subscription” a little too seriously 😅
@sama Sam, I’ve burned through 56.7 billion tokens in Codex since March 22. I’ve built an iOS messenger, AI tools, and a game with my 6-year-old son. Codex didn’t just help me write code. It changed what I believed I could build.