» Tag
llm
472 postsTessera: An Open-Source AI Agent Layer That Refuses Answers Without Proof
Tessera is a deterministic AI agent framework that unifies enterprise data into one knowledge graph and refuses to answer without traceable evidence.
Why LLM Apps Must Be Engineered as Distributed Systems
A production AI app broke under load—not because of the model, but missing queues, caching, retries and observability. Backend engineering is the real differentiator.
Final Token Preference Optimization Tackles Reasoning Model Doom Loops
Antidoom uses Final Token Preference Optimization to fix repetitive doom loops in reasoning models, cutting loop rates sharply in LFM2.5 and Qwen3.5 without broad model degradation.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comKV Cache Quantization's Effect on KLD in Qwen3.6-27B
A KL-divergence benchmark on bartowski's Qwen3.6-27B GGUF quants (Q8/Q6/Q5) shows KV cache quantization at (q8_0,q8_0) preserves quality almost for free.
New study finds language models memorize about 3.6 bits per parameter
Researchers unveil a method to measure LLM memorization capacity, finding GPT-style models store roughly 3.6 bits of information per parameter, with implications for grokking and scaling.
Subtext Visualizes an LLM's Internal Reasoning in Real Time
Subtext is an open-source tool that applies Anthropic's Jacobian lens to visualize a local LLM's internal representations live during conversation.
Layer-First Pattern Cuts LLM Overload in Map Generation
RidgeText stores map layers server-side instead of passing raw GeoJSON to the LLM, cutting tool-call context from roughly 125,000 tokens down to about 150.
Encoding Team Standards into AI Instructions
Why senior engineers' tacit knowledge causes inconsistency in AI-assisted development, and how it can be turned into executable, versioned instructions.
Building a Model-Agnostic Vulnerability Discovery Harness
Project Glasswing details a model-agnostic security harness that scans 128 repos across a fleet, avoiding lock-in to any single frontier AI model.
Scaling LLM Usage with LiteLLM: Monitoring, Quotas and Spend
Midas engineers explain how they built a unified LiteLLM gateway to centralize LLM observability, spend tracking, and per-environment quotas.