zenlikethat
Joined 14 years ago
Karma
1,542
Submissions
509
Member since
Mar 28
Recent submissions
Comment · 1 month ago
Comment · 1 month ago
> I assume this isn't really for consumers/individuals currently?
Unless they're hackers, no. It's not really a chat interface, it's meant for consumption by machines and composing into higher level systems (pairs great with LLMs).
> Is there somewhere to read more about that? I assume customers would just have some tests or talk to you.
We're going to release some more info on evaluations over time, and yeah, join the waitlist! We offer faster access in exchange for good memes
Comment · 1 month ago
Yeah that's precisely correct.
For e.g. classification tasks, even in 2026 people are doing things like hallucinating deliberately, and then matching the hallucinations to embeddings -
https://softwaredoug.com/blog/2026/08/10/hypothetical-classi...
With TypeSafe it just picks the class (actually probabilities across classes), reliably every single time.
Comment · 1 month ago
It's pretty darn smart. If you did want to hack on it in earnest and find out for yourself, send me an email - [email protected]
Comment · 1 month ago
love it. send me an email and i'll try to get you moved up on the list? [email protected]
Comment · 1 month ago
Nothing, but imagine using LLMs for a classification task
People out there are so resigned to the models being unreliable that they are really doing things like hallucinating deliberately, and then matching the hallucinations to embeddings -
https://softwaredoug.com/blog/2026/08/10/hypothetical-classi...
You could do that or you could just... use a model that will never produce unreliable outputs in the first place.
Comment · 1 month ago
Not in the traditional sense of a coding agent, but we think there's a ton of opportunity in using it for context management ("do we _really_ need to pass all these tokens to the agent?"), semantic linting ("how does this score against this AGENTS.md: <...>"), etc.
Comment · 1 month ago
join the discord! we love forward thinkers
Comment · 1 month ago
That's kinda the goal. Imagine all the automation in the world being able to embed intelligence directly inside it - factories could route based on more complicated questions, hardware could anticipate your needs. Customer support could be done without humans 90% of the time.
Comment · 1 month ago
Yeah, it doesn't output strings, just decisions/answers.
Comment · 1 month ago
The model can't reason comprehensively (e.g., like Sol XHigh would to solve a complicated problem), but it's designed to be able to answer anything a human reasonably could quickly and intuitively, i.e., system one thinking: https://en.wikipedia.org/wiki/Thinking,_Fast_and_Slow
Comment · 1 month ago
It's a bit hastily put together, but I made a dspy fork where you can add a decorator to automatically use TypeSafe where possible on Signatures. It shows a fair bit of what actual, hands on usage looks like.
Comment · 1 month ago
Strings trigger us
Comment · 1 month ago
It's very generalized. Can't wait until everyone can see it.
Comment · 1 month ago
> the model takes as input a state (structured text? not sure if multi-modal)
Input, and criteria/instructions can both be defined as structured input (JSON). This ends up being pretty powerful because the model is trained to understand structure.
e.g.: https://docs.typesafe.ai/primitives/advanced#structured-inst...
> not sure if multi-modal
just JSON... for now :)
> outputs the question's answers as appropriate
correct!
(2-3) No, but that's kind of a sick cook ... Want to get access and try it? [email protected]