> plan mode has always been a prompt — it has never changed the toolset because doing so would break the prompt cache, and so would be expensive

seems like plan mode could turn off some tools, even if it doesn't change the set offered to the model, the ones that they have which would mutate your codebase could just not work with an error message, and plan mode could change permissions in the security approval prompt for "auto"

anyway, isnt the right way to know if plan mode helps or not, to run an experiment? we're all guessing unless we have data

read only agent mode sounds straightforward and useful to me

It’s bizarre to me that Claude Code doesn’t have more guardrails on plan mode. I mostly use Copilot and the plan mode there has teeth. In plan the agent does not have permission to write to the filesystem outside of a temp directory and the plan document itself, and tool calling is heavily restricted.

There’s also a “ask” mode which is read only. Both are enforced by the permissions model, not just a system prompt instruction. I’ve seen the model “forget” and try to start coding - it bounces off a hard permissions failure and that “reminds” it that it’s in plan mode.

Brute force is guaranteed to eventually find the most efficient possible solution (in an extremely inefficient manner, assuming you run it long enough)

I feel cosmology ought to grapple more with, “Why is there something rather than nothing?” That question and this question are certainly linked. If expansion is a mirror of collapse, how do we get from some initial nothingness to a point where there is something capable of collapsing? Starting with an infinite amount of stuff everywhere feels like cheating.

But that’s cosmogony, not cosmology. Cosmology can just explore the cosmos that is there not having to worry about why it came to be. If there’s a causality of causality, then what’s the cause of itself.

huh, i never heard of cosmogony, that's cool, thank you

Even with efficiency breakthroughs, it would just afford packing more agents per unit of memory. Scaling compute and data keeps paying off, leading to smarter models, and smarter models have more demand even at higher prices because they can accomplish more work at higher quality. Sovereign AI hasn’t even really taken off yet to anywhere near the level it could. That’s going to dramatically increase the number of massive-scale users of AI agents. So no, IMHO they will “never” have “enough.”

At some point though, won't someone be able to extrapolate the demand growth curve, and invest some colossal amount of money into making and selling more RAM chips?

Yes. China's done just that. Expect those factories to come online within 2-3 years.

Weve hit the sigmoid. Whats scalling is ancillary to the model. The cry for a slowdown is because the open weight models demonstrate the cost of parameter pacling is not work neither inference nor training.

The assumption about the singularity simply is a delusion with LLMs.

However, the models do provide a means to improve the harness universe, so that residual will continue to improve perception. Parameter cpunt will stagnate and training wont be justifiable from every angle.

Me, Is self-awareness thermodynamically favorable? (2015) https://docs.google.com/document/d/1Ed9ikW47Key-jYZy0CNZH75q... - “the probabilistic nature of reality is what drives Life and forces the evolution of self-aware consciousness”

Have you looked at the logistic map as well? There's a fourth domain there. O:-)

whoa

I feel like Nike’s biggest fumble was not advertising the Invincibles more. It seemed they had some evidence the PEBAX foam could reduce injury in base mileage, which is the number one thing many/most runners spend the most time on. So why not make sure everybody knows this? It seems weird. If you have a lot of athletes who need conditioning and don’t want to get injured, why not advertise the crap out of the injury prevention shoes?

I think the API runs on Azure

Hosted on Azure is different from provided by Azure. The former just uses Azure as an infra provider. The latter is a managed offering that is operated and billed by Microsoft using tech licensed from OpenAI.

I personally think this acquisition is genius anybody who could afford it would be wise to own HuggingFace because they are incredible

I think it’s a bunch of hidden UTF-8 character substitutions so the text looks the same but the underlying bytes are different

Thanks, that makes a lot of sense. I wonder however how can this be done without giving a lot of problems when copypasting or sending the input to other LLMs (not even thinking about code here).

I was wrong here, it’s more about the RNG they use for the word choices [1]. Although I wouldn’t be surprised to see UTF-8 substitutions also.

[1] https://www.anthropic.com/news/claude-text-watermark

It’s amazing how much Python punishes you for modularizing your code