Ren v1.1.0, October 31, 2026See the weights

Secnd is a research lab building AI that decides, and knows when to ask.

Our models take a situation and a list of options, return one option with a probability, and hold back when they can't prove that's safe.

See the resultsGet the weights

Connections (planned)

So much of what makes your work yours is the way you decide: what you approve, what you push back on, what you let wait. It takes years to learn, and it's the hardest part of you to hand to anyone.

We believe a model can learn it. Software should be able to carry your judgment, act on it when it's sure, and come back to you when it isn't.

Knowing when to ask matters as much as knowing the answer. A model that can't say "I don't know" can't be left alone, however often it's right. Trust has to be earned one decision at a time, with proof you can check.

Diagram. Three inputs, situation, options and examples, feed Ren inside a frame labelled Secnd. Ren reads, weighs, picks and checks, then passes its answer to the gate. The gate sends it to one of two outputs: act or ask. A return wire runs back to Ren, labelled: with consent, real decisions train the next Ren.

Ren reads a situation and its options, and a gate decides whether it can act alone or must ask.

Research, then products

Decision models.
Text models are built to generate. Decisions need speed, low cost and knowing when not to answer, so we train models for that job alone.
Proof of when to trust them.
Accuracy says a model is often right. We measure how many decisions it can handle alone, with proof, per dollar, and publish where it fails.
Secnd, our first product.
It will connect to your work tools, learn how you decide, act when it's sure and ask when it isn't. It's in development.
See the results

Ren, measured

We publish our results, including the weak ones.

Time per decisionOne decision
Time for one decision
GPUNot counting the network26ms
EndpointMedian, India to one GPU in the US424ms
CPUOn CPU2.18s
Training data12 licensed public sets and 26 written ones422,906 rows38 sets
ComputeTo train RenAbout $129
Answered aloneAt our 99% gate

MTOP 21.0% answered alone, 1 error in 923 answers, lower confidence bound 99.40%.

BANKING77 0% answered alone, because it couldn't prove it was safe.

Typed decisionsMixed test, 2,000 decisionsLevel with OpenDecider-nano.
  1. 75.4%OpenDecider's run of Jev 1.13
  2. 79.6%OpenDecider-nano
  3. 79.7%Ren
Test accuracyFixed official test sets
Data table
Test accuracy, in percent
SetSeriesNo examples8 nearest32 nearest
MTOPRen v1.1.075.99%92.38%93.59%
MTOPSame training, seed 078.64%92.93%93.23%
BANKING77Ren v1.1.068.99%89.90%86.23%
BANKING77Same training, seed 068.90%90.62%87.44%
Limits

One seed with full history. It doesn't certify a new business. No real business has run Ren yet. Jev scores 79.7% on BANKING77 with no examples and costs about $0.008 per 1,000 decisions, against Ren's $0.083.

Run Ren yourself.

  1. On a GPU

    001

  2. On a CPU

    002

  3. In your own cloud

    003

Weights are public under CC BY-SA 4.0. With consent, real decisions from Secnd will train the next Ren.

Latest

Roles: We aren't hiring yet.