OneTriangle
The cheapest, fastest lightweight inference.
About OneTriangle
Inference has surpassed training as AI’s largest compute cost, accelerated by increasing demand for AI and agents. By using proprietary KV cache transfer tech, OneTriangle has cut inference costs by 20% and time by 40% compared to present standards.
Public traction evidence
Each signal links to the public source used for attribution.
- X
@OneTriangleAI (YC S26) is building the fastest lightweight, cheap inference and hosting @deepseek_ai V4 Flash today at $0.15/M input and $0.35/M output tokens.
@OneTriangleAI (YC S26) is building the fastest lightweight, cheap inference and hosting @deepseek_ai V4 Flash today at $0.15/M input and $0.35/M output tokens. Live at https://t.co/WB4uyRBzaN. Our group of @MIT grads and olympiad medalists from @GoogleDeepMind,
- X
We’re in YC! Here’s what we’ve been up to: > Dropped out of MIT > Rejected our NYC quant and banking offers > Moved to SF > Fixed br...
We’re in YC! Here’s what we’ve been up to: > Dropped out of MIT > Rejected our NYC quant and banking offers > Moved to SF > Fixed broken AI adoption with personalized one-click automations @TryTrustAI Excited to put everything into our product, great start to a new chapter.
- X
We gave AI agents access to real production systems and watched them do things they were never authorized to do.
We gave AI agents access to real production systems and watched them do things they were never authorized to do. SOC 2 and ISO can't catch it, but @TryTrustAI can. We built new evals so companies can have a continuous, transparent record on key vulnerabilities, get suggested...
- X
@TryTrustAI is building the fastest, cheapest lightweight inference by optimizing KV cache at @ycombinator.
@TryTrustAI is building the fastest, cheapest lightweight inference by optimizing KV cache at @ycombinator. Our group of MIT grads and olympiad medalists from @GoogleDeepMind, @JaneStreetGroup, and NeurIPS/ICML publishers are setting a new standard for cost and latency
- X
hi it’s Hannah! Also new to X, here’s my intro > from wisconsin + korea > cs & econ @MIT > prev. @VirtuFinancial, @WorldBankGroup > ...
hi it’s Hannah! Also new to X, here’s my intro > from wisconsin + korea > cs & econ @MIT > prev. @VirtuFinancial, @WorldBankGroup > CEO @TryTrustAI (YC S26) > excited for the batch! > tennis + travel enthusiast bullish on interaction models, automation maxxing, and teams where...
- X
We beat out @nvidia's KV cache transfer for KL divergence, and we're using it to build the fastest inference @TryTrustAI at @ycombinator.
We beat out @nvidia's KV cache transfer for KL divergence, and we're using it to build the fastest inference @TryTrustAI at @ycombinator. 17.8% less TTFT, $641 less per 1M requests, and 82.5% held-out top-1 agreement on Qwen 32B, prefilled from Qwen 8B.
- X
We just made AI that reads your mind and automates for you. TrustAI (@TryTrustAI) understands your context across the browser (CRMs, in...
We just made AI that reads your mind and automates for you. TrustAI (@TryTrustAI) understands your context across the browser (CRMs, internal tools, Slack, GitHub) and suggests personalized automations you can run in one click. Accept, tweak, or ignore, then keep working while...
- X
Buying AI ≠ Adopting AI. Get fast, personalized one-click automations with @TryTrustAI, backed by @ycombinator. Demo list live at http:...
Buying AI ≠ Adopting AI. Get fast, personalized one-click automations with @TryTrustAI, backed by @ycombinator. Demo list live at http://auto.trytrust.ai.