Tarun Ajjarapu

mts @judgmentlabs

[Tarun Ajjarapu @tarajj00]

@alexshander03 @JudgmentLabs ts so tuff

[Alex Shan @alexshander03]

Today, @JudgmentLabs opens for general access.

We believe long running agent systems will generate more exhaust data than the world can currently process.

Hidden within agent traces are rich records of how to make these systems better: what users ask for, when agents stumble, and how agents interact with the external world.

Judgment is the most performant monitoring and improvement layer for long-horizon agents.

We’re excited to see what you build!

[Tarun Ajjarapu @tarajj00]

excited to share what ive been working on this past few months!

Judgment Labs is now open for general access ‼️

it's been an insane journey building at the frontier of AI agents. ignore the orange suit at the start (that aint me, trust 😭)

[Alex Shan @alexshander03]

Today, @JudgmentLabs opens for general access.

We believe long running agent systems will generate more exhaust data than the world can currently process.

Hidden within agent traces are rich records of how to make these systems better: what users ask for, when agents stumble, and how agents interact with the external world.

Judgment is the most performant monitoring and improvement layer for long-horizon agents.

We’re excited to see what you build!

[Neel Ajjarapu @neelajj]

ChatGPT Slides is the best AI-native slide editor for advanced charts and data analysis

You can built and edit everything from combo charts to trendlines, error bars, treemaps, and more

These aren't static images. They are real, editable charts. You can edit them directly in ChatGPT, export them natively to PowerPoint, and modify the data in Excel

[Tarun Ajjarapu @tarajj00]

prove the rust compiler next pls🙏

risc-v has a relative small / clean isa, lowk modeling its operational semantics is tractable. x86 is crazy tho, generating instruction level semantics precise enough to reason about compiled binaries without trusting the compiler is insane. no glaze tho, trust😭

[Anthropic @AnthropicAI]

New on our Frontier Red Team blog: using Claude to formally verify software at large scale.

Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).

With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.

Read our research in full here: https://t.co/zUyx8CjBEk

[Tarun Ajjarapu @tarajj00]

…

[Tarun Ajjarapu @tarajj00]

@JudgmentLabs immaculate

[Tarun Ajjarapu @tarajj00]

people really be going for more runs than walks these days

[Tarun Ajjarapu @tarajj00]

there’s no limit to the larp…

[Tarun Ajjarapu @tarajj00]

how much u gotta hate someone to pour ts out 😭