Genomics, Bioinformatics & Machine Learning
Ever heard of an AI agent harness? Well, you re almost certainly interacting (even implicitly) with at least one of those every day π If you think of the LLM as a car engine, the agent harness is everything around it that lets you actually drive the car: the steering, brakes, controls, navigation and connections to [ ]
TL;DR: Agentic AI is not just making work faster. It is turning work into fast-moving loops of planning, coding, testing, deployment, and iteration. In biology and pharma, this creates a new challenge: not simply whether agents can produce useful outputs, but whether humans can steer these loops toward the right questions, the right assumptions, and [ ]
Why the Next Frontier in AI Is Not Intelligence, but Reliability AI has made starting work almost free.But it has quietly made supervising that work far harder. Artificial intelligence has dramatically lowered the cost of starting cognitive work: Write a document.Generate a dataset analysis.Prototype a system.Spin up an agent. Tasks that once took days now [ ]
TL;DR: Agentic AI is most powerful when it frees users from rigid interfaces and helps navigate open-ended reasoning spaces; the key is applying it where flexibility and synthesis matter, not everywhere by default. Agentic AI has opened up a genuinely new way of building software. For the first time, complex systems can be explored in [ ]
Moving From Tool-Calling to Code Execution In the past year, AI systems have started behaving less like static models and more like dynamic collaborators, connecting to tools, APIs, databases, and cloud systems on our behalf. Yet as this ecosystem grows, weβre hitting an increasingly familiar ceiling: context overload. Large models can plan, reason, and synthesise [ ]
Iβve been reflecting on how π¨π° ππππππ built on large language models communicate, not with 0s and 1s but through tokens, hinting at a quiet shift in how information behaves. π‘ For decades, the πππ was the indivisible unit of information: binary, context-free, and precise. But as autonomous agents reason and converse, the πππππ seems [ ]
The Transformer model, introduced in the paper Attention is All You Need , has literally transformed modern natural language processing (NLP) and ignited the (re-) emergence of whole new other AI fields (most notably Generative AI). The model s power lies in its encoder-decoder architecture and the self-attention mechanism, which is amenable to extreme parallelisation and thus [ ]
π I am thrilled to share our advancements in therapeutic target discovery with Mantis-ML 2.0, now published in Science Advances! π Phenome-wide identification of therapeutic genetic targets, leveraging knowledge graphs, graph neural networks, and UK Biobank data #AstraZeneca #AI #Genomics Mantis-ML 2.0 is an ensemble #ML framework designed to comprehensively harness the wealth of existing [ ]
The battle for Greece s next top model may have been over for this year πHowever, the battle s still on in almost every machine learning task a data scientist comes across in their daily -and nightly- lives. The long standing questions in these cases are: Fortunately, the machine learning community can offer some real engineering gems for [ ]
Ever had an encounter with the most awkward programming language? Surely, awk may have a slightly awkward name, possibly a bit awkward syntax at times but overall it s far from being considered awkward as a language. In fact, it is one of the most powerful tools any programmer should possess to nail simple or more complex [ ]