If we assume resources are infinite, any effort would look ridiculous. To achieve great goal, we have to limit ourselves deliberately on some aspects.
It reminds me that "compression is intelligence". By limiting the parameter space, the LLM could extract deep representation from training data.
Why is a plan "mode" needed? I really hate reading plans in conversation UI. One line in AGENTS.md is always better, and you can customize it to fit your document convention.
From the communication perspective, the planning process is most about creating clarity and alignment, on things like scope, constraints and decisions, among people (and agents now), often requiring multiple rounds. The planning tool built in Codex or Claude Code is not persisted, version-controlled, nor well accessible.
In practice, My AGENTS.md contains an instruction about writing a document before starting implementation. Usually I won't read that document, because I don't want to micromanage agents. That document mostly serves a historical purpose like ADR, helping me find out what agents missed, made mistakes on or misaligned on, if needed.
However, the bank is happy to extend the loan infinitely for people with enough assets. It's questionable that whether such loans are cash flow neutral.
>However, the bank is happy to extend the loan infinitely for people with enough assets.
Long maturity products still have to be repaid. There are no "infinite" maturity loan products for retail customers.
>It's questionable that whether such loans are cash flow neutral.
There's zero question: loans are cash flow negative (for customers) with interest. Banks are not going to offer products that are not cash flow positive for the bank.
kind of a bold claim without evidence, but sedentary lifestyle does seem to play a role.
what does not matter for most people is nebulous objectives like "mobility" or "good posture".
but yea, everyone should lift weights for various reasons, not just to reduce the chance of random pain.
I'm interested in how to integrate formal verification with existing software libraries. For example, https://github.com/verus-lang/verus integrates proof with macro in Rust. What's the plan for Bend?
It looks like a Transformer encoder post-trained on classification and regression tasks. The encoder-only model is less noticed in recent years, but this product finds a nice application for it.