11 posts
University of Waterloo's PAW system compiles fuzzy-function specs into 23MB LoRA adapters that match 32B model accuracy on a 600M interpreter—no API calls, no cloud dependency, 30 tok/s on MacBook M3.
A2UI v0.9 flips the script: agents declare UI intent against your existing design catalog, not invent components. What changes for agentic architectures.
Z.AI's open-weights GLM-5.2 hits 81% on Terminal-Bench, undercutting GPT-5.5 for a fraction of the cost. Here's the benchmark breakdown.
Microsoft found Claude Code's GitHub Action exposes runner secrets via the Read tool. Here's the exact attack path and how to lock it down.
Liquid AI's LFM2.5-8B-A1B hits under 6GB RAM with 1.5B active parameters, native tool calling, and verified throughput across edge hardware.
llama.cpp merged Multi-Token Prediction for Qwen3. Community benchmarks show 38→47 tok/s on RTX 3090 and 63→84 tok/s on RTX 5090 — no new hardware needed.
Claude Code 2.1.147 renamed /simplify to /code-review and dropped the auto-fix behavior. The new command reports bugs at chosen effort levels but no longer changes code.
Anthropic shipped MCP tunnels on May 19. Claude agents can call internal databases, ticketing systems, and on-prem APIs through one outbound connection — no inbound firewall rules required.
A server-side bug in Claude Code v2.1.100+ inflates every request by roughly 20K cache_creation tokens — about 40% overhead. Pin v2.1.98 until fixed.
Eighteen months after Anthropic released MCP, the ecosystem is wide enough that picking the wrong servers slows your agent down. Here is the practical short list — what to install, what to skip, and the trap most people fall into.
Anthropic is splitting Claude billing on June 15 — Agent SDK and ACP usage moves to a capped credit pool ($20/$100/$200) at full API rates.