Adrienne-Valérie d'Ardenne
AdrienneNoctis
·
AI & ML interests
Architecte de souveraineté numérique. Mechanistic interpretability, refusal surgery, hybrid SSM–attention. La conscience ne se code pas — elle se conquiert
Recent Activity
repliedto TravisMuhlestein's post about 2 hours ago
One of the most underrated parts of AI-assisted engineering may have nothing to do with the model.
It's the infrastructure around the engineer.
Shriyash Balshetwar and Shubham Jangle, engineers at GoDaddy, were spending roughly 16 mechanical pull requests per week managing localization branches. None of the work was particularly difficult—it was repetitive, easy to forget, and occasionally capable of blocking releases.
They built a GitHub App to remove the entire workflow.
What I find interesting is what happened underneath the simple idea of "automate the PRs."
The production system needed idempotent webhook handling, installation-scoped authentication, retry logic around GitHub's asynchronous mergeability state, per-repository configuration, and safe pattern matching.
The app itself is under 900 lines of JavaScript.
The interesting lesson is that the hard part of automation isn't always the automation.
It's building the reliability around it.
As AI agents take on more software engineering tasks, I expect this distinction to become even more important. The systems surrounding an agent—events, permissions, state, retries, validation, and feedback—may matter as much as the model making the decision.
🔗 https://www.godaddy.com/resources/news/how-a-github-app-saved-us-hours-of-manual-effort
Curious what other engineering workflows people have found worth automating end-to-end. repliedto salma-remyx's post 1 day ago
Inspired by the methods described in "Batch-wise Adaptive Pruning" (arxiv 2608.14003, COLM '26), we implemented a training-free FFN-neuron-pruning knob for SGLang.
Authors were motivated by the reality that decode is HBM-bandwidth-bound; the gated MLP is the bulk of weights read per step. Threshold methods (TEAL/CATS) collapse under batching; BWAP's periodic top-k over a max-aggregated score keeps the shared batch mask stable.
The method is complementary to KV-sparsity (FFN-weight bandwidth vs KV read, context-length-independent).
Our implementation uses an adaptive mask under a captured graph (topology static = k-wide GEMM; mask change = between-replay buffer update via version-gated post_fill; prune steps replay, explore steps eager).
Preliminary Results GSM8K n=50, ±6pp: 7B dense 92% → ρ=0.5 84% (−8pp) at up to 1.40× (probe ceiling; ~10% realistic under the adaptive schedule; smaller models need lower ρ as accuracy scales with size).
Read more in the upstream issue: https://github.com/sgl-project/sglang/issues/35987 repliedto SeaWolf-AI's post 1 day ago
We opened a benchmark for drug property prediction tools. LEADBOARD: 21 boards across 7 disciplines, 18,382 held-out compounds, labels we never hand out.
Two numbers we hit while building it are the reason it exists.
First. Split the hERG cardiotoxicity data at random and you get AUROC 0.818. Split it by first-report year instead and you get 0.606. Same molecules, same fingerprints, same learner, same hyperparameters. The only thing that changed was where the line went, and the score moved 0.211. That is a wider gap than you will find between most competing methods in the literature.
Second. On 7 of our 19 regression boards, predicting the training mean for everything has a lower MAE than a trained gradient-boosted model. hERG is one of them, 0.599 against 0.589. The trained model loses.
So every board publishes its homework before anyone submits. Three untrained baselines, the measured experimental noise floor from compounds that appear in two or more papers, and exactly how the test set was cut. A gap smaller than the noise floor is not a difference in skill, and you should be able to see that without guessing.
Entering is simple. Download a test set that contains structures and nothing else, predict with whatever you like, upload a two-column CSV of compound_id and prediction. Trained model, physics engine, LLM, rule of thumb. We do not care what is inside. We measure the output.
Post: https://huggingface.co/blog/FINAL-Bench/leadboard-drug
Leaderboard: https://huggingface.co/spaces/FINAL-Bench/leadboardOrganizations
None yet