Tokenware is the new form of donation

Do we already have a tokencurrency btw? A tokencoin?

Hey that’s an interesting idea, wouldn’t be surprised to see it become very popular very soon

Do you intentionally want to assume each feature costs a fixed value (be it number of tokens or $ etc)?

In my experience, as features are added, the cost of other features fluctuate (can be cheaper or more expensive). Thus building software often requires figuring out what NOT to build and managing complexity.

I’m a strategist, not a tactician!

To me it sounds pretty reasonable though to settle a price for the feature, it’s the same as what we do working with customers, they say, “hey, I need this button to be red,” and we respond “two billion bucks bro, and it’s red.”

I am usually able to implement whatever is needed, but I want to stop (or at least decrease an amount) paying my own money for the requested features.

I think you are right, and that tokens themselves can be a form of universal currency just like MCP+LLM forms a kind of universal glue between software. We tried to defend micropayments for content and support multiple times but worse alternatives always settled.

Maybe issues tagged with [tokens: 300k, accepted_models: opus-4.7-xhigh, pr_review: [opus>=4.6, gpt>5]] will become the norm. You provide the plan and prompt to orient the donator’s agent in your codebase, and they provide cost of implementation and review.

Since last week I strongly believe there will be tooling to apply an agentic conversation to a codebase, just like you can publish patches by email. Instead of providing the resulting PR, you provide the whole conversation that generates the PR, but the edits are there as inline patches and the whole transcript can be fed into a git CLI or GUI to see the diff. So you can’t masquerade a PR of sonnet 3.5 quality for an opus 4.7 one.

An interesting new kind of PoW.

Turns out we’re all in energy business (again).

How does it matter? Also, I am not using Claude for its miserable RAG, and proper solutions always involve several providers for different kinds of tasks.

I disagree we need to judge by the model used (it’s like judging the code quality by number of LoCs.) If I could have it done with local ollama—I’m good, I deserve a reward.

This is all not about donations, let alone control. I just want to be able to support my OSS better without breaking $1K/month limit on that, as I stated in the post above.

Well cost is often used as a proxy for effort or investment, and different models have different per-token cost. But I think I misunderstood your initial post : I understand someone pays for the tokens, but who burns them through an agent ? You or the person who sponsors ?

If the person burns their tokens to provide a PR, the whole sponsorship thing is out of scope. I just accept or reject a PR, that’s it.

Sure. And I am too greedy to buy cheap stuff, as my father used to tell me. On average, the tokens-per-feature is nearly constant across providers.