There's an asterisk right below that table stating that:
> *Anthropic reported signs of memorization on a subset of problems
And from the Anthropic's Opus 4.7 release page, it also states:
> SWE-bench Verified, Pro, and Multilingual: Our memorization screens flag a subset of problems in these SWE-bench evals. Excluding any problems that show signs of memorization, Opus 4.7’s margin of improvement over Opus 4.6 holds.
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.
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.
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.
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)
> *Anthropic reported signs of memorization on a subset of problems
And from the Anthropic's Opus 4.7 release page, it also states:
> SWE-bench Verified, Pro, and Multilingual: Our memorization screens flag a subset of problems in these SWE-bench evals. Excluding any problems that show signs of memorization, Opus 4.7’s margin of improvement over Opus 4.6 holds.