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
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.
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
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
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
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.
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
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
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.
"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
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
In AI, the days are long but the years are short. Although some days are dog years…
2
0
2
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
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
It is only once a paper has been searched for via the Bing index that the picture content becomes indexed.
1
0
0
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
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
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
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
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
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
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
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
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