Image created with Gemini. Image prompt: Hand-painted Studio Ghibli style square cover of a sunlit seaside archive shop with a wall of labeled card-catalog drawers and books, a young librarian holding up a smiling porcelain mask with rose-blush cheeks while paper slips flutter from open drawers toward the mask, a quieter human face half-visible behind it, warm terracotta rooftops and teal harbor through the window, soft gouache watercolor backgrounds and golden-hour light, a wooden shop sign above the door with bold clean painted lettering spelling RAG.
This year, the local model is becoming critical infrastructure at every scale: – the individual (privacy, cost) – the company (data control, cost) – the nation (resilience) @rasbt’s new writeup walks through setting this up locally, with a nod to @cohere’s North Mini Code”
https://x.com/JayAlammar/status/2071950697096987040
Excited to see @cohere open-source how they use AI coding agents to maintain their vLLM fork. 🙌 Keeping a long-lived fork in sync is tricky. Their agent treats it as a control loop: rebase onto each upstream release, run tests, diagnose, fix, repeat until green. Weeks of work”
https://x.com/vllm_project/status/2070364532296536346
Semantic search alone doesn’t cut it. Neither does brute-force grep. Agents need both. Today we’re shipping the Retrieval Harness in LlamaParse Index: semantic search, server-side grep, and file-level navigation working together in a single agent reasoning loop. 🦙🌤️ Grep a”
https://x.com/llama_index/status/2071656315210826006
Somewhere in my agent’s memory, two versions of the same fact are still arguing. That’s the whole problem with agent memory in one sentence. A bigger context window doesn’t fix it. It just delays when you notice. More tokens, more cost, and eventually worse retrieval as the”
https://x.com/PrajjwalYd/status/2072291317695324410
We’re excited to introduce the Retrieval Harness in LlamaParse – which is the 2026 version of RAG over documents Generalized agents need the right set of tools to scalably search and read through an arbitrary corpus of data (from 10 docs to 1m+ docs). They can already”
https://x.com/jerryjliu0/status/2071729856900215261
Great paper on managing agent skills. Skill libraries keep growing, and picking the right skills has become a bottleneck for coding agents. The defaults are to expose the agent to the whole skill collection, or retrieve skills with embeddings and rerankers. Both treat the”
https://x.com/omarsar0/status/2072430551446032847
If your benchmark relies on a static dataset or sampling from a static distribution densely known at training time, then it is fundamentally measuring memorization/retrieval. Which might be fine if you’re looking for a retrieval benchmark! But don’t confuse it with intelligence.”
https://x.com/fchollet/status/2070554884999692698
A great source to understand or refresh Transformer architecture It explains how transformers process text token by token, using self-attention to build contextual representations Covers: – Token embeddings and positional encodings – The residual stream that carries”
https://x.com/TheTuringPost/status/2072876709284852116
because grep alone wasn’t a good solution. there were plenty of solutions between “passive semantic rag” and “grep the entire codebase”. Why not LSPs that warn the model that it’s doing it wrong, or hybrid BM25-semantic indices over the codebase, with active tools to look up what”
https://x.com/max_paperclips/status/2071465351959998723
Leave a Reply