Luke Marsden (@lmarsden) 's Twitter Profile
Luke Marsden

@lmarsden

CEO @helixml - Private GenAI Platform helix.ml. Owner mlops.consulting. Founder mlops.community. Hacker & entrepreneur

ID: 21925637

linkhttps://helix.ml calendar_today25-02-2009 21:58:39

3,3K Tweet

2,2K Takipçi

2,2K Takip Edilen

Hamel Husain (@hamelhusain) 's Twitter Profile Photo

. Shreya Shankar 's paper confirms what I see in practice 1) Automated evals don't work (without semi-manual human alignment) 2) Most tools don't provide this alignment 3) Automated evals add mostly noise 4) You can only write good evals by looking at data and reacting to failures

. <a href="/sh_reya/">Shreya Shankar</a> 's paper confirms what I see in practice

1) Automated evals don't work (without semi-manual human alignment)
2) Most tools don't provide this alignment
3) Automated evals add mostly noise
4) You can only write good evals by looking at data and reacting to failures
Luke Marsden (@lmarsden) 's Twitter Profile Photo

Here we make our first foray into coding assistants - with an **open source** MCP server that indexes many private repos, making your code assistant smart when it comes to private, internal enterprise coding conventions. Can't wait to integrate this into helixml

Phil Winder (@drphilwinder) 's Twitter Profile Photo

Kodit 0.3 Released: - 10× faster indexing - Private Azure DevOps support - Pre-filter searches - Auto-indexing - Slick CLI progress bars blog.helix.ml/p/kodit-03-10x…