Fixing LLM memory degradation in long coding sessions
Long-session LLM memory degradation (entropy) is the silent killer of complex coding projects. Models like Gemini, GPT-4, and Claude all suffer from it, leading to hallucinations and lost context. I've developed an open-source protocol that temporarily "fixes" this issue by structuring the dialogue. It's not the final architectural solution, but it’s a proven patch for developers working right now. Looking for feedback from the community on how we can solve this structurally. https://github.com/robertomisuraca-blip/LLM-Entropy-Fix-Prot...
Does the same job
all alternatives →
- ZLZep – Long-Term Memory Store for LLM Apps2023 · ▲7
Zep is a long-term memory store designed for conversational AI applications built using modern LLMs. It handles the storage, summarization, embedding, indexing, and enrichment of chat histories, and offers developers a simple, low-latency API to this data. Chat history storage is an infrastructure challenge all developers and enterprises face as they look to move from prototypes to deploying conversational AI applications that provide rich and intimate experiences to users. Key features include long-term memory persistence, auto-summarization, vector search, auto-token counting, and Python…
- ILImprove LLM Performance by Maximizing Iteration Speed2024 · palico.ai · ▲5
LLM Application development is extremely iterative, more so than any other types of development. This is because in addition to all the activities involved in regular application development, we also need to make the LLM Application accurate and reduce hallucination. To improve performance, we need to trial and error various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, try different agent architecture, and more. There are thousands of permutations to try. We need to be able to easily experiment with these…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology