Sean Ward @DNAEngineer

CEO & Co-founder @iGent_AI. Previously Founder @synthace, Relatable, Scale DX igent.ai London Joined March 2011

Tweets

1K
Followers

2K
Following

894
Likes

539

Sean Ward @DNAEngineer

6 days ago

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

0 0 2 106 1

View Details

@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.

0 0 0 9 0

View Details

Sean Ward @DNAEngineer

4 months ago

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

1 0 2 16 0

View Details

Sean Ward @DNAEngineer

4 months ago

@jonas @dbreunig @karpathy @grok We did Redis last July: igent.ai/insights/produ…. The truth is, specification is the bottleneck (and a well known system shortcuts that).

0 0 0 26 0

View Details

Claude @claudeai

7 months ago

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.

1K 2K 19K 7.8M 3K

View Details

Sean Ward @DNAEngineer

8 months ago

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

0 0 0 73 0

View Details

Sean Ward @DNAEngineer

8 months ago

@unit_accord @Yuchenj_UW x.com/dnaengineer/st…

Sean Ward @DNAEngineer

8 months ago

@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: igent.ai/insights/produ… with repo of results and all commit/session history.

0 2 24 921 14

0 0 2 78 0

View Details

Sean Ward @DNAEngineer

8 months ago

@_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.

0 0 3 961 0

View Details

Sean Ward @DNAEngineer

8 months ago

0 2 24 921 14

View Details

Sean Ward @DNAEngineer

9 months ago

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

9 months ago

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

1 4 11 1K 1

0 0 0 588 0

View Details

Sean Ward @DNAEngineer

9 months ago

@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. igent.ai/insights/produ… is several man years in the course of ~70 hours or agent time however.

0 0 1 61 0

View Details

Sean Ward @DNAEngineer

10 months ago

@simonw Strong recommendation: it takes a very different promoting strategy to maintain attendance across that context: basic system prompt + context + request alone won’t cut it.

1 0 1 857 0

View Details

Sean Ward @DNAEngineer

10 months ago

@platonovadim @_xjdr Yes, tests are central including leveraging the existing redis client libraries and benchmarks. The entire commit history also shows every round of the AI workflow during building.

1 0 3 210 0

View Details

Sean Ward @DNAEngineer

10 months ago

It has become clear there is a massive performance and productivity delta growing between engineers who understand and embrace AI, with appropriate tooling and critical analysis, and those who have have remained in the co-pilot era. Never before has it been so possible for those who know what they are doing, to build so much.

iGent AI @iGent_AI

10 months ago

Tired of toy AI demos that fizzle in production? iGentAI built Ferrous: A Rust Redis-compatible server outperforming Valkey. 35KLOC, 100% test passing, beats benchmarks. Zero human code. Built in 70 hours of part-time direction. Toys vs. tools—here's the proof.

1 4 13 2K 2

1 0 0 708 1

View Details

iGent AI @iGent_AI

a year ago

Our VibeCodeBench evaluations affirm what @Anthropic just announced: Claude Sonnet 4 excels at autonomous multi-feature development. We've seen codebase navigation errors drop from 20% to near zero and strategic refactoring that saves ~500k tokens on multi stage, complex tasks. Proud to power Maestro with this breakthrough.

Anthropic @AnthropicAI

a year ago

Introducing the next generation: Claude Opus 4 and Claude Sonnet 4. Claude Opus 4 is our most powerful model yet, and the world’s best coding model. Claude Sonnet 4 is a significant upgrade from its predecessor, delivering superior coding and reasoning.

928 3K 21K 4.3M 3K

1 3 7 558 2

View Details

Louis Knight-Webb @tokengobbler

a year ago

It's always great hosting @AITinkerers London meetups right after a new model drops... Huge thanks to @rebecca_harbeck from @AnthropicAI, as well as the @iGent_AI team @MSzummer and @samshapley for giving impromptu talks with tons of learnings from early access Claude Sonnet 3.7. We also got to see @HarryCoppock from the @AISecurityInst live demoing 3.7 hacking into a docker container 🫢 And as always, we had some fantastic product, behind-the-scenes and benchmark beating agent talks from Emma Burrows, @moeadham and Sergei Petrov. Huge thanks to team @localglobevc and @ferdisigona for making it happen!

9 3 14 903 0

View Details

Sean Ward @DNAEngineer

a year ago

At @iGent_AI, we’ve found @AnthropicAI new Sonnet 3.7 to be quite the powerhouse. Everything from debugging multi language distributed systems, to comprehending and updating legacy codebases, to rapid prototypes or POCS of new technologies. Agentic SWE is now here.

iGent AI @iGent_AI

a year ago

"Agency > Intelligence" @karpathy nailed it, and after 18 months building Maestro, we agree. The real AI leap isn’t just smarts—it’s agency: the ability to act independently, turning assistants into partners.