Simone Civetta
@viteinfinite.bsky.social
Interesting, it's kind of counterintuitive. But will try.
June 19, 2025 at 4:40 PM
Interesting, it's kind of counterintuitive. But will try.
📊 Telemetry
No data is collected by Apple via telemetry.
No data is collected by Apple via telemetry.
June 17, 2025 at 7:23 AM
📊 Telemetry
No data is collected by Apple via telemetry.
No data is collected by Apple via telemetry.
🧪 Adaptor Training Toolkit
Allows model adaptation via Fine-Tuning (presumably LoRa) but, as mentioned in the videos, you should re-run the FT each time the underlying model is updated (which means at every iOS release or so)
Allows model adaptation via Fine-Tuning (presumably LoRa) but, as mentioned in the videos, you should re-run the FT each time the underlying model is updated (which means at every iOS release or so)
June 17, 2025 at 7:23 AM
🧪 Adaptor Training Toolkit
Allows model adaptation via Fine-Tuning (presumably LoRa) but, as mentioned in the videos, you should re-run the FT each time the underlying model is updated (which means at every iOS release or so)
Allows model adaptation via Fine-Tuning (presumably LoRa) but, as mentioned in the videos, you should re-run the FT each time the underlying model is updated (which means at every iOS release or so)
🔐 Safety model
A built-in guardrail AI model is automatically added and enforced by Apple.
It cannot be modified or disabled. No API for building your own as of now.
A built-in guardrail AI model is automatically added and enforced by Apple.
It cannot be modified or disabled. No API for building your own as of now.
June 17, 2025 at 7:23 AM
🔐 Safety model
A built-in guardrail AI model is automatically added and enforced by Apple.
It cannot be modified or disabled. No API for building your own as of now.
A built-in guardrail AI model is automatically added and enforced by Apple.
It cannot be modified or disabled. No API for building your own as of now.
🔄 Background inference
Foundation Models framework supports background inference!
But subject to system-level constraints:
– Rate-limited
– Cancelled during camera or AAA games usage
– Throttled or terminated in case of resource pressure
Foundation Models framework supports background inference!
But subject to system-level constraints:
– Rate-limited
– Cancelled during camera or AAA games usage
– Throttled or terminated in case of resource pressure
June 17, 2025 at 7:23 AM
🔄 Background inference
Foundation Models framework supports background inference!
But subject to system-level constraints:
– Rate-limited
– Cancelled during camera or AAA games usage
– Throttled or terminated in case of resource pressure
Foundation Models framework supports background inference!
But subject to system-level constraints:
– Rate-limited
– Cancelled during camera or AAA games usage
– Throttled or terminated in case of resource pressure
⚙️ Hardware execution
Runs primarily on ANE (Apple Neural Engine).
This means you can use GPU while running inference — but prolonged concurrent usage can cause system stress, which may lead the system to terminate your app, even if in foreground.
Runs primarily on ANE (Apple Neural Engine).
This means you can use GPU while running inference — but prolonged concurrent usage can cause system stress, which may lead the system to terminate your app, even if in foreground.
June 17, 2025 at 7:23 AM
⚙️ Hardware execution
Runs primarily on ANE (Apple Neural Engine).
This means you can use GPU while running inference — but prolonged concurrent usage can cause system stress, which may lead the system to terminate your app, even if in foreground.
Runs primarily on ANE (Apple Neural Engine).
This means you can use GPU while running inference — but prolonged concurrent usage can cause system stress, which may lead the system to terminate your app, even if in foreground.
🧬 Model versioning
Same model version across all supported devices — no per-device variation. Whether you’re running an old iPad, the latest iPhone or even macOS, it’s exactly the same model. Perfect for testing and consistency across your multiplatform apps!
Same model version across all supported devices — no per-device variation. Whether you’re running an old iPad, the latest iPhone or even macOS, it’s exactly the same model. Perfect for testing and consistency across your multiplatform apps!
June 17, 2025 at 7:23 AM
🧬 Model versioning
Same model version across all supported devices — no per-device variation. Whether you’re running an old iPad, the latest iPhone or even macOS, it’s exactly the same model. Perfect for testing and consistency across your multiplatform apps!
Same model version across all supported devices — no per-device variation. Whether you’re running an old iPad, the latest iPhone or even macOS, it’s exactly the same model. Perfect for testing and consistency across your multiplatform apps!
🔢 Context size
Not officially documented as it might change anytime.
But today the limit stands at 4096 tokens.
Not officially documented as it might change anytime.
But today the limit stands at 4096 tokens.
June 17, 2025 at 7:23 AM
🔢 Context size
Not officially documented as it might change anytime.
But today the limit stands at 4096 tokens.
Not officially documented as it might change anytime.
But today the limit stands at 4096 tokens.
Sure. That said, it’s not about models but about features: Cursor has agent modes, custom modes, MCP integration and frequent updates. I don’t see how Xcode can keep up with this, but I hope to be wrong.
June 16, 2025 at 6:27 AM
Sure. That said, it’s not about models but about features: Cursor has agent modes, custom modes, MCP integration and frequent updates. I don’t see how Xcode can keep up with this, but I hope to be wrong.
Oops, forgot mentioning.
I’m on the Beta, it wouldn’t work otherwise.
I’m on the Beta, it wouldn’t work otherwise.
June 14, 2025 at 3:16 PM
Oops, forgot mentioning.
I’m on the Beta, it wouldn’t work otherwise.
I’m on the Beta, it wouldn’t work otherwise.
On macOS, System Language and Siri must be set to the same language (and the setting is irritantly reflected on your iPhone). Then make sure Apple Intelligence is turned on.
At that point it should work.
(Or at least it does for me. I’m using English (UK))
At that point it should work.
(Or at least it does for me. I’m using English (UK))
June 14, 2025 at 12:04 PM
On macOS, System Language and Siri must be set to the same language (and the setting is irritantly reflected on your iPhone). Then make sure Apple Intelligence is turned on.
At that point it should work.
(Or at least it does for me. I’m using English (UK))
At that point it should work.
(Or at least it does for me. I’m using English (UK))
Ha! Try again or double check the settings on the simulator. (Maybe locale / language?) It should work. (Unless I hallucinated last night)
June 14, 2025 at 11:55 AM
Ha! Try again or double check the settings on the simulator. (Maybe locale / language?) It should work. (Unless I hallucinated last night)
By far the Foundation Models framework. Wonderful API IMO, and so feature rich.
June 14, 2025 at 11:51 AM
By far the Foundation Models framework. Wonderful API IMO, and so feature rich.
Can’t agree more. For what it’s worth I submitted it as a feedback in the satisfaction form.
The level of “self-referential” of the last two videos is cring-ish.
The level of “self-referential” of the last two videos is cring-ish.
June 14, 2025 at 9:54 AM
Can’t agree more. For what it’s worth I submitted it as a feedback in the satisfaction form.
The level of “self-referential” of the last two videos is cring-ish.
The level of “self-referential” of the last two videos is cring-ish.
Why do I feel such a strong urge to try your alarm app?
June 10, 2025 at 3:10 PM
Why do I feel such a strong urge to try your alarm app?