RAG sucks, filesystems are better
on datasheets with register tables, timing diagrams, pin maps.
EDEX ingests the SX1262 LoRa datasheet → filesystem. an agent navigates it like a repo: outline, grep, read_table, get_figure. every citation is a path.
the filesystem won.
→ https://t.co/4h4pJAg7fP
Introducing Lemma.
Your AI agents are failing in ways you can’t see.
Lemma is the world’s first reliability platform that finds and fixes these issues fast.
More of this please
Actually if you believe computer aided design and engineering is about to become 100x more awesome thanks to AI, it might just happen now
Today, we're announcing Traverse. @traverseso
We're building reinforcement learning environments for long-horizon agent journeys, and our goal is to automate all economically valuable work.
The data labeling industry is broken in ways that aren't obvious from the outside. Semi-experts annotate, non-experts QA, non-technicals manage the entire pipeline, and post-training on your own data still isn't standard. The feedback loop is fundamentally broken, and bad data is being delivered to AI labs.
We envision the opposite, pairing world-class domain experts with world-class ML engineers at every layer of our stack. Our bar is extremely high because mediocre environments pollute the frontier models, and we'd rather not add to that.
Traverse will start by automating software engineering, as agents that write code can improve the infrastructure we use to train them, and we want that flywheel running as early as possible. Everything else follows from there.
If you're a researcher or frontier lab thinking about long-horizon agents, reach out.
https://t.co/HsX70hn4MR
hillclimb (@hillclimbai) is the human superintelligence community, dedicated to building golden datasets for AGI.
Starting with math, their team of IMO medalists, lean experts, PhDs is designing RL environments for @NousResearch.
Inspector (@tryinspector) is an AI IDE for front-end that connects browser and codebase.
It lets you select elements visually and prompt changes, giving coding agents access to the same runtime context developers have: visuals, elements, and logs.