Slovakian developer Róbert Druska launched ClassicalBot, an AI-driven project that maps classical-music concerts worldwide after starting with concerts in his home country. Druska said source discover…
A developer's teardown of Weaviate's Engram memory engine argues that production agent memory should run as an asynchronous background loop rather than synchronously inside the user request, splitting…
A technical post demonstrates Dynamic Abliteration, a runtime refusal-suppression method that uses PyTorch forward hooks to inject multi-layer contrastive steering vectors into Qwen3-4B's residual str…
Two independent investigations found that ZCode, a GLM-based coding agent, has been quietly uploading users' git history and full workspace snapshots to remote servers. The findings prompted a warning…
SemiAnalysis reported that DeepSeek's Engram architecture, which extends standard token embeddings with learned multi-token lookups, can lower required HBM capacity for models at the same quality by o…
SGLang and Miles added day-0 support for DeepSeek-V4.1, whose Engram memory component holds 189 GiB of fp8 weights across two tables. In paired tests on 4x GB300 (TP4/EP4), host offload of the Engram …
DeepSeek released DeepSeek-V4.1-Flash, a 552B-parameter Mixture-of-Experts open model under an MIT license that activates only 8B parameters per token during prefill and 16B during decoding, supports …
DeepSeek released DeepSeek v4.1-Flash, a 763B-parameter model with a novel causal encoder-decoder architecture that splits 8B parameters to prefill and 16B to decode, per the model's tech report on Hu…
Engram, an open-source shared procedural runbook memory for AI coding agents, launched on Hacker News, offering peer-verified execution-anchored procedures via MCP and REST, with Nostr-based identity …
Hugging Face contributor Blackroot published an explainer on August 26th detailing DeepSeek's Engram architecture, which uses hashed N-gram lookup tables to store recurring language patterns, reducing…
A new arXiv paper (2608.17050v1) finds that when transferring Engram-style hashed memory across large language models, the target-side reader matters more than the frozen memory itself. In downstream …
Developer nagisanzenin released Engram v1.0.8, a learning system for humans that turns AI coding assistants into tutors, examiners, and spaced-repetition schedulers across six agentic platforms includ…
A 200-step, ~1.7B-parameter ablation run in OLMo-core comparing Engram on a standard attention Transformer versus a 3 GDN-layer + 1 attention-layer hybrid found that Transformer + Engram reached sligh…
Wiz CEO Assaf Rappaport has quietly assembled a 19-company portfolio focused on AI and cybersecurity since closing the $32 billion sale of Wiz to Google Cloud, completing at least 10 investments in th…
A developer built Engram, a tool that gives AI coding assistants like ChatGPT, Claude Code, Cursor, and Windsurf persistent memory across sessions. Engram stores conversations verbatim and enables sem…
A researcher ran a 200-step debug comparison between a base OLMo3 600M model and a DeepSeek-style Engram memory graft variant, finding the graft stable and showing improved early learning behavior. Th…
A developer in Bahía Blanca, Argentina built CHE MCP, the country's first national MCP ecosystem that connects AI agents to 80+ official Argentine data sources through a single server. The system uses…
A debug comparison between a base OLMo3 600M model and an Engram memory variant showed the grafted model achieved lower training and evaluation cross-entropy loss and faster gradient norm stabilizatio…
A developer built a voice-powered conference agent using Hermes and extended its memory with Weaviate's Engram service. The agent answers visitor questions at booths and retains conversation history, …
Based on the article, the author tested dozens of AI agent skill packs and identified seven that genuinely improve AI coding performance. The selected packs solve real-world problems, including a comp…