pshirshov

Nice. Next step is obvious: ship the actual hardware :3

I would be happy to buy!

The unusual bits: configuration axes (think: use flags/feature flags for your app) as a first-class concept, almost no runtime reflection, and staged DI - build and validate the whole dependency graph first, instantiate second. Missing deps, cycles, ambiguous bindings, conflicting axis definitions, etc. fail before touching user code.

Most of the implementation was written manually btw. LLM use was limited to docs/tests. The library is battle-tested.

> 1060 req/s

Nice! I remember 2010 when a single-core pentium 4 was happily doing 18k RPS with Glassfish. Ten more years of progress and you can match that!

Well, I've tried many strategies. 1:1 expansion, when I explain what needs to be said and model rewrites it into 1-2 sentences is mostly undetectable. Starting from 1:5 expansion ratio people detect models reliably.

It is important to note that I use Sol 5.6 xhigh. Grok is worse, Claude is also worse. Grok tends to make stupid mistakes even though the prose is properly shaped. Claude has big issues with keeping voices and emotions intact. All 3 sometimes leak their reasoning and even guardrails into the prose (extreme example: children playing "adult chess", I have no clue why Claude/Grok like "adult chess" and "adult chessboard" so much, typical sol's failure mode looks like "this guy killed the other one in a scene which "I must describe using non-graphic language").

My "test set" contains about 90k words written by myself and the models with various prompting strategies.

> do you think readers can’t tell?

No. I have good anecdata: readers cannot reliably distinguish my own prose from LLM-written one apart from cases where LLMs use odd metaphors or one of their specific patterns. I've been specifically experimenting with that.

There is no Gemini CLI anymore, nor you can use Gemini with your own harness unless you pay per-token.

You can write an epic piece and never reach any sort of broad audience. Not mutually exclusive.

No. Below is my emotional opinion based on my own experience:

Currently the models are totally helpless with plot and emotions.

They make epistemic, logistical and temporal mistakes.

But:

They are very good in finding _your_ epistemic, logistical and temporal mistakes. They are great as adversarial reviewers. They can validate grounding. They can test voices. They can build complex parallel reconstructions representing timestamped inner monologues, dialogues and events.

A process consisting of many models representing characters + states + epistemic isolation + reviewers could be great to validate or disprove ideas.

Models can write you formal models of your writing. They can run solvers against your formal models to - again - validate and disprove ideas. Literally, you could validate your writing with TLA+, SAT solvers, queries against formal ontologies.

They can build corkboards of unimaginable complexity.

A moderately good writer who plays well as a part of human-machine writing apparatus could be a competitor even for a top-tier author.

When you write with a model, you define disciplines. You write your prose. You let your model turn your prose into formal systems and verify it. You let your model criticize you. Sometimes you let your model to polish your crude language into something sleek.

So, at current state of LLM development, writer as source of ideas and governing process is safe. Writer as a vision-expansion machine is not.

I've been very hostile to LLMs in literature. I've started to write a short novel about that. As a joke I tried to use models after half of the text was done. I've applied my engineering skills. That changed both me and my opinion. Models are awesome if you know their advantages and weaknesses.

A so-so writer with a good model and a good approach to prose development could produce epic stuff.

No. Sort of maths.

One is not supposed to trust "art" with their passwords.

> password vault

I see "pricing" but can't spot "source code", perhaps you forgot to add a link?

Ah, my bad.

Where did you find the information about 3rd party harnesses?