Just a heads up that this is completely broken as of 2.0.76.
Dug through their obfuscated JS and it looks like they forgot to re-add a function call in the LSP manager initialize function that actually adds/indexes the lsp registered from plugins.
ChatGPT has 2 types of memory: The “explicit” memory you tell it to remember (sometimes triggers when it thinks you say something important) and the global/project level automated memory that are stored as embeddings.
The explicit memory is what you see in the memory section of the UI and is pretty much injected directly into the system prompt.
The global embeddings memory is accessed via runtime vector search.
Sadly I wish I could disable the embeddings memory and keep the explicit. The lossy nature of embeddings make it hallucinate a bit too much for my liking and GPT-5 seems to have just made it worse.
No real modulation or switching occurs.
If you start a new chat, your “explicit” memories will pretty much be injected right into the system prompt (I almost think of it as compile time memory). The other memories can sort of thought of as “runtime” memory: your message will be queried against the embeddings of your chat memories and if a strong match is made, the model will use the embedding data it matches against.
kool aid or not -- "reasoning" is already part of the LLM verbiage (e.g `reasoning` models having `reasoningBudget`).
The meaning might not be 1:1 to human reasoning, but when the LLM shows its "reasoning" it does look _appear_ like a train of thought. If I had to give what it's doing a name (like I'm naming a function), I'd be hard pressed to not go with something like `reason`/`think`.
It gets even more confusing! If you're on the "Premium" plans (i.e the the old standard "Google One" plans) and upgrade to >=5TB storage, your "Premium" plan starts including all the features of "Google AI Pro".
Tip: If you do annual billing for "Premium (5 TB)", you end up paying $21/month for 5TB of storage and the same AI features of "Google AI pro (2TB)"; which is only $1/month more than doing "Google AI Pro (2 TB)" (which only has monthly billing)
Guessing you mean the McDonalds on Pandora? I remember going there a lot during high school and walked by it again recently while visiting the city for the the first time since 2009. Sketchy doesn't begin to describe it. Was really sad to see what happened to the city I grew up in.
Canada currently has an issue with handing out way too many student visas to students going to strip mall diploma mills. I believe the federal government has just enforced a cap for the next 2 years.
You can reenable the web interface in iCloud settings under system preferences on a Mac (not sure if it’s on iOS). The web interface will require just in time verification with an iCloud device to confirm log ins though. Works pretty well.
It would still break end-to-end encryption if I allow it.
However I just found out Apple added a way to manage rules in iCloud Mail to iOS 17. It's in Settings > [Your Name] > iCloud > iCloud Mail > iCloud Mail Rules. They did not mention this anywhere, but it's there and it's new!
Unfortunately still unusable for me because it allows only a single condition. No AND or OR conditions. For example still not possible to filter by FROM and Subject and the same time. And you can only filter a very limited amount of fields: FROM, TO, FROM or TO, CC, Subject and List-ID. For example it's not possible to search the body.
iCloud Mail and Calendar are way too simple to be useful for me. Calendar only searches 1 year back, even if everything is synced (I actually need this quite often). No weekly view in portrait mode (I use this all the time in Google Calendar). Calendar and Reminders don't integrate at all (Google Calendar shows tasks from Google Tasks). Not possible to sync calendar subscriptions across devices.
Its incredibly powerful! One downside is variables captured in the match are lifted to the function level. The lack of block level scoping in the match statement leads to a lot of people shooting themselves in the foot by overwriting a variable that they didn't intend to. On a personal note, I find the 2 levels of indentation to reach the case body to be too much as well... but that's just a personal preference.
Dug through their obfuscated JS and it looks like they forgot to re-add a function call in the LSP manager initialize function that actually adds/indexes the lsp registered from plugins.