Sean Ward Profile
Sean Ward

@DNAEngineer

Followers
2K
Following
552
Media
43
Statuses
1K

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

London
Joined March 2011
Don't wanna be here? Send us removal request.
@DNAEngineer
Sean Ward
2 months
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
2 months
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
0
0
0
@DNAEngineer
Sean Ward
3 months
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
@iGent_AI
iGent AI
3 months
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.
0
0
0
@iGent_AI
iGent AI
6 months
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.
@AnthropicAI
Anthropic
6 months
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.
1
3
7
@LouisKnightWebb
Louis Knight-Webb
9 months
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
9
3
14
@DNAEngineer
Sean Ward
9 months
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
9 months
"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.
0
1
2
@LouisKnightWebb
Louis Knight-Webb
1 year
Hottest week for London AI so far 🔥 Dev Day yesterday and AI Tinkerers tonight! https://t.co/6NhMejSYvL @monzo @tortus_AI @_lucas_godfrey @QuotientAI @samshapley @LukeHarries_ @stephenbtl
0
6
28
@DNAEngineer
Sean Ward
2 years
In AI, the days are long but the years are short. Although some days are dog years…
2
0
2
@DNAEngineer
Sean Ward
3 years
There is also clearly a deep semantic analysis taking place on the image content, such as understanding iconography and the contextual meaning of it for a given document
0
0
1
@DNAEngineer
Sean Ward
3 years
How does this multimodal capability appear to work? An interesting differential is the reported token length of the retrieved pdf document. In contrast, the underlying text represents around 12k tokens.
1
0
1
@DNAEngineer
Sean Ward
3 years
It is only once a paper has been searched for via the Bing index that the picture content becomes indexed.
1
0
0
@DNAEngineer
Sean Ward
3 years
This capability does not appear to exist for local documents summarized via the Bing chat extension in edge, which is only able to reason atop the textual content in a pdf.
1
0
0
@DNAEngineer
Sean Ward
3 years
Interested in having access to multimodal GPT-4 to ask questions using vision as well as text? While @OpenAI has yet to make it available, it appears that you can access it today via @bing Chat. Requests that involve pdf papers can answer questions about figures and pictures
2
1
8
@DNAEngineer
Sean Ward
3 years
The GPT-4 accessible today is still limited to a 4k token context, which begins to cause it to forget as a task progresses and it runs out of context. However, with a 32k context available in preview, this is clearly the future of R&D. And it already has ideas on improvement...
0
0
0
@DNAEngineer
Sean Ward
3 years
GPT-4 then developed a Bayesian optimization system to model & sample hyperparameters for further improvement. The investigation was grounded in code, forming & testing hypotheses, and using larger datasets to evaluate algorithmic changes to enhance ML performance.
1
0
0
@DNAEngineer
Sean Ward
3 years
The benchmarks (written by GPT-4) evaluated accuracy, training time & inference times. A 50% speedup was observed using LRA & sparse matrices! This led to GPT-4 expanding the evaluation to a CNN with the MNIST dataset, resulting in a similar 30% speedup vs traditional approaches.
1
0
0
@DNAEngineer
Sean Ward
3 years
Exploring ways to improve ML model inference speed, GPT-4 via ChatGPT+ identified Low Rank Approximation & sparse matrices as a promising approach. It rapidly created Python programs to benchmark performance on the classic Iris dataset with a simple linear neural network.
1
0
1
@DNAEngineer
Sean Ward
3 years
I observed the system changing strategies based on tool outcomes, showing that it can adapt and learn from its mistakes. As these systems continue to progress, applying this technology in synbio, materials science, and other scientific grand challenges is borderline sci-fi.
0
0
0
@DNAEngineer
Sean Ward
3 years
The implications of AI systems being able to write AI systems themselves are enormous. Also, by expanding the library of tools that AI models like ChatGPT can interact with, we open up new possibilities for innovation and automation.
1
0
0
@DNAEngineer
Sean Ward
3 years
It used the python interpreter to systematically debug the code it was generating, including working through problems such as accessing API keys, out of date documentation, and even debugging the quality of the output from the code generation tool it wrote!
1
0
0
@DNAEngineer
Sean Ward
3 years
By enabling ChatGPT to interact with tools such as a Python REPL and a vector index of python docs, it was able to break a problem into manageable pieces. It used the Python REPL to debug the code it generated and work through issues like accessing API keys and outdated docs
1
0
0