Sean Ward

CEO & Co-founder @iGent_AI. Previously Founder @synthace, Relatable, Scale DX

[Sean Ward @DNAEngineer]

Maestro (our research agent for problems measured in man decades and centuries) and I wrote them in five days, on Claude Fable 5.1.

@claudeai did not co-author it. Not yet externally reviewed.

[Sean Ward @DNAEngineer]

Post-quantum encryption and RSA.

The hardness numbers next to both are the cheapest attacks anyone has written down. They are not the cheapest attacks those methods themselves allow.

We computed the second number for both. We did not break either.

[Sean Ward @DNAEngineer]

Certified means an exact certificate and a second checker. Everything else is labelled. If a certified claim cannot be rebuilt from the repo, that is a bug.

[Sean Ward @DNAEngineer]

@logangraham @hannu The barrier hasn’t been technology: it has been regulatory stance and belief

[Sean Ward @DNAEngineer]

@ctjlewis It is more complicated than that however: most providers brainfried their models with RL to go prompt -> outcome. Anthropic models can maintain competing hypothesis and tension for far longer, which allows thesis, investigation, correction, and autonomy.

[Sean Ward @DNAEngineer]

@ctjlewis In its simplest terms: Anthropic models can reason. Hello from the days of Spellcraft btw.

[Sean Ward @DNAEngineer]

@jonas @dbreunig @karpathy @grok We did Redis last July: https://t.co/B82cjMvQqf. The truth is, specification is the bottleneck (and a well known system shortcuts that).

[Claude @claudeai]

Introducing Claude Opus 4.5: the best model in the world for coding, agents, and computer use.

Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.

[Sean Ward @DNAEngineer]

@sqs You are assuming those are at odds with each other

[Sean Ward @DNAEngineer]

@unit_accord @Yuchenj_UW https://t.co/0qHVtKX4Fn

[Sean Ward @DNAEngineer]

@Yuchenj_UW Verifiable engineering tasks, mostly at the scale of entire features, primarily in compiled languages like go or rust, where it can validate the outputs and hill climb. One such public example: https://t.co/B82cjMviAH with repo of results and all commit/session history.

[Sean Ward @DNAEngineer]

@_xjdr It natively wants you to be absolutely right (it is Sonnet after all). However, unlike 4.0, it will listen to style and tone instructions on a long horizon basis.

[Sean Ward @DNAEngineer]

@Yuchenj_UW Verifiable engineering tasks, mostly at the scale of entire features, primarily in compiled languages like go or rust, where it can validate the outputs and hill climb. One such public example: https://t.co/B82cjMviAH with repo of results and all commit/session history.

[Sean Ward @DNAEngineer]

The world is rapidly bifurcating between those who have experienced the superhuman capabilities of even current generation models, used properly, and those stuck in the capabilities of the past.

[iGent AI @iGent_AI]

We're excited to share that our agent, Maestro, drafted solutions to all 12 problems from ICPC 2025 World Finals in ~2 hours - using current models, no human involvement, no internet access. We deeply respect the human teams' extraordinary dedication. Note: no official validation

[Sean Ward @DNAEngineer]

@SimonInmania @matthewclifford Yes, task length is in Replit’s case measured in agent runtime, which can slightly proxy for the metric that really matters: how many man months (or years) of work the agent performs. https://t.co/B82cjMviAH is several man years in the course of ~70 hours or agent time however.