TextLayer

TextLayer helps enterprises and ambitious teams build, deploy, and scale advanced AI systems—without rewriting their infrastructure.

[TextLayer @textlayerai]

We appear to be in our Jev era.

Gareth, our AI Architect, did the obvious thing: gave @typesafeai's Jev control of a rocket in Kerbal Space Program.

TL;DR: this is very cool. His learnings in the comments.

@hackgoofer, @CompleteSkeptic, @EGafni — is this as good as Doom?

[TextLayer @textlayerai]

Directly transferable to AI Agent trace observability (decisions, tool calls, reasoning, branching). This was so much fun. Off to go add more struts.

[TextLayer @textlayerai]

We appear to be in our Jev era.

Gareth, our AI Architect, did the obvious thing: gave @typesafeai's Jev control of a rocket in Kerbal Space Program.

TL;DR: this is very cool. His learnings in the comments.

@hackgoofer, @CompleteSkeptic, @EGafni — is this as good as Doom?

[TextLayer @textlayerai]

SRE alerting (hand "degraded" not "p99=847ms"). If you don't know your labels/classifications you probably don't know your problem space.
Jevediah can review the entire launch logs of a mission + with an LLM, provide insights for how state should be handled on the next mission.

[TextLayer @textlayerai]

If AI can make thousands of decisions a second, the architecture starts to change.

Ex-OpenAI researcher Diogo Almeida’s TypeSafe just emerged from stealth with Jev, a model built for fast, structured decisions inside software.

Our engineering channel lit up almost immediately.

[TextLayer @textlayerai]

Our engineers have been saying this for a while, the job is to choose the right tool for each part of the system.

There's still plenty to prove before enterprise puts something like Jev into critical workflows.

But this is a really interesting direction for production AI.

[TextLayer @textlayerai]

If AI can make thousands of decisions a second, the architecture starts to change.

Ex-OpenAI researcher Diogo Almeida’s TypeSafe just emerged from stealth with Jev, a model built for fast, structured decisions inside software.

Our engineering channel lit up almost immediately.

[Diogo Almeida @CompleteSkeptic]

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?

I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev

• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions

AFAICT the shortest path to AI-based economic revolution

[TextLayer @textlayerai]

Use language models where you need reasoning or generation. Use System One or System Two models where the job is a fast, bounded decision.

Use deterministic software where the rules are already known.

[TextLayer @textlayerai]

We’re live.

TextLayer helps you ship impactful, production-quality AI for your users in weeks, not quarters.

Modular infra. Senior engineers. Real results.

🌐 https://t.co/IYLd3GuFvq

We’re hiring:

➡️ AI Engineer
➡️ AI Product Manager

[TextLayer @textlayerai]

What a week! Listed on @TheRundownAI and @Futuretools_io and passed 700 registered users 🔥🤯📈

Thank you for all the support while we #buildinpublic!