prose 0.9.0 just released. It has this new nice dashboard that gives you a summary of your work across sessions.
It also has a feature to do explicit handoff between agent-session (cross agent harness).
https://t.co/XeDrrISKn7
11.5h/day is a decent average. What's yours?
@mufcbacker@QuinnyPig I see that perspective. But it feels like it would just be simpler to lower the quotas than actually burn GPU-cycles.
I am comparing money spent with quality of service, and engineered inefficiency isn't a good way to keep me as a customer.
Yet here I am, $3K+ later.
@mufcbacker@QuinnyPig I really don't understand this angle.
They're giving me a service. I pay the same, $200/month. Why is it beneficial for Anthropic to burn more tokens than less?
I've seen this take before, but I never got to the bottom of the reasoning.
Composer also uses this term a lot. They're like kids who just learned a new cool term and want to impress everyone all the time.
Also, dev-lingo they seem to be settling on:
- Slice
- Frontier
- Fork (not the Git-kind)
It's been a while since I did enterprise-coding, but I don't remember these things we talked about every 4 minutes. I might be out of touch on this one and it could be establish language with the cool kids.
All development is gap-closing. If you cannot measure where you are and know where you're going, the LLM cannot effectively reason about whether the gap is being closed or not.
So design your system to be ultra transparent and testable. The more you can float of data to the LLM to ensure correctness, the more it can iterate over. Runnable artifacts are better than prose, often by a lot.
The reason why people are loving Rust for agentic development is that the compiler gives you a literal runnable representation of the gaps that needs to be closed.
If you can model this into your domain so that requirements are also runnable, repeatable and deterministic, you'll be having a better time.
Verification as a runnable artifact = You don't have to verify.
Create these harnesses with agentic coding, have the LLM help you brainstorm and implement it together.
Spend more time on this extended harness than on the core product in the beginning. But always prioritize the extended harness over the shipped artifact; the shipped artifact is literally downstream from your extended harness.
Hope this helps.
All development is gap-closing. If you cannot measure where you are and know where you're going, the LLM cannot effectively reason about whether the gap is being closed or not.
So design your system to be ultra transparent and testable. The more you can float of data to the LLM to ensure correctness, the more it can iterate over. Runnable artifacts are better than prose, often by a lot.
The reason why people are loving Rust for agentic development is that the compiler gives you a literal runnable representation of the gaps that needs to be closed.
If you can model this into your domain so that requirements are also runnable, repeatable and deterministic, you'll be having a better time.
Verification as a runnable artifact = You don't have to verify.
Create these harnesses with agentic coding, have the LLM help you brainstorm and implement it together.
Spend more time on this extended harness than on the core product in the beginning. But always prioritize the extended harness over the shipped artifact; the shipped artifact is literally downstream from your extended harness.
Hope this helps.