Viewing profile — xdotli

How do labs train a frontier, multi-billion parameter model? We look towards seven open-weight frontier models: Hugging Face’s SmolLM3, Prime Intellect’s Intellect 3, Nous Research…

Author here. We built 5 high-fidelity mock Google Workspace + Slack services and ran 7,224 trials across 6 frontier models and 4 agent harnesses. The headline finding that surprise…

A two-week study of autonomous language model agents deployed in a live multi-party environment with persistent memory, email, shell access, and real human interaction — tested by …

Agent scaffold comparison. We additionally evaluateOpenCode, an open-source scaffold that supports multiplemodel providers. Native CLI scaffolds consistently outper-form OpenCode w…

yeah we didn't give agents access to the internet for creating their domain knowledge skills

The Register wrote about works on SkillsBench.ai

no worries it's totally fine! there is indeed work needs to be done on the feedbacks generated skills. Thanks for helping us submitting on HackerNews. And for > a lot of Skills on …

20+ Anthropic Default Skills, 200k+ community skills on skillsmp. People talk about skills without knowing how well they work. We're hosting the largest Agent Skills hackathon at F…

Did you check our repos and sites? the repo is skills native. Also please don't be misled by the original title, we have this configuration to eliminate the impact of internal know…

We collected 86 tasks from 105 domain experts across 11 domains, every task is verifiable, human created and has verified Skills. SOTA model without skills score ~30% without skill…

we didn't create that headline yeah thanks for liking it

Thanks @dang for moderating! This is indeed not our original findings and this is a sub conclusion for an ablation we did to remove the confound of LLMs internal domain knowledge. …

I would frame the 'post-trajectory generated skills' as feedback-generated skills, so is Letta: https://www.letta.com/blog/skill-learning . We haven't seen existing research or hyp…