SPIFFE for AI Agents: The Workload-Identity Problem, and the Half It Doesn't Solve
The industry is treating 'agent identity' as a new frontier. It's actually two old, solved problems bolted together — and the interesting failure lives exactly at the seam between them.
5 min
Run a 671B Model on One 24GB GPU: The MoE Offload Trick, KTransformers vs llama.cpp
A frontier mixture-of-experts model has 671B weights but touches only ~37B per token. That gap is why you can serve DeepSeek-scale models on a single consumer GPU — if you split by tensor role, not by layer.
6 min
The RL Environment Boom: Why Training AI Agents Is Suddenly Worth More Than the Model
Money and talent are pouring into 'RL environments' — the training gyms where agents learn by doing. The catch is that an environment is only as valuable as a reward you can't hack, and for the tasks that matter most, that reward is provably hard to build.
4 min
Why AI Agents Ignore Their Own Instructions — and How Parlant Enforces Them
A system prompt is a broadcast: every rule you add competes with every other rule for the model's attention, on every turn. Parlant's bet is that reliability is a context-assembly problem, not a prompt-writing one.
6 min
Orchestrator-Worker vs Pipeline vs Swarm: How to Choose a Multi-Agent Topology
The three multi-agent shapes aren't ranked best-to-worst — they're a single axis. Pick by one question: how much context can you afford to lose between agents?
4 min
Multi-Region LLM Failover: Uptime Is the Easy Part — Your Cache and Your Data Residency Are the Bill
The managed cross-region inference you turned on already solved availability. It did it by dissolving the region boundary you may be legally required to keep — and by throwing away your prompt cache at the exact moment you're already degraded.
5 min
Why the Top Agent-Memory System on LongMemEval Stores Everything Verbatim — and Runs No LLM
MemPalace tops the long-term memory benchmark by refusing to summarize. That's not a trick — it's an argument that the field spent two years solving the wrong half of the problem.
5 min
Liquid AI's LFM2.5-230M: A 230M On-Device Model Built to Route and Extract, Not Reason
Liquid AI's smallest model yet fits in under 400MB and runs on a Raspberry Pi. The interesting part isn't how small it is — it's what a model this size is actually for.
4 min
LangGraph's DeltaChannel: The Hidden Quadratic Cost of Durable Agents
Every checkpoint a long-running LangGraph agent writes re-serializes its entire state. DeltaChannel, per-node timeouts, and the v2 stream in 1.1–1.2 are the runtime quietly admitting the naive durability model doesn't scale.
4 min
How to Pull Structured Data From Long Documents — and Trace Every Field Back to the Source
Schema-constrained output gives you a valid object. It can't tell you whether a value was read from the document or invented to satisfy the schema. Google's LangExtract returns the exact character span each field came from — which turns extraction from a trust exercise into a verification one.
4 min
GAIA, Explained: The Benchmark That Stopped Measuring Your Model
On GAIA, the best base model sits near 45% while orchestrated agent systems clear 92% — matching humans. That 47-point gap isn't noise. It's the benchmark quietly telling you the model was never the thing under test.
4 min
Two in Five Public MCP Servers Have No Authentication — and OAuth Didn't Save the Rest
The first internet-wide measurement of remote MCP servers found 40.55% wide open. The surprise isn't the unlocked doors — it's that the servers that did add OAuth were flawed 100% of the time.
5 min
Environments Hub vs HUD vs Gymnasium: Where RL Environments for Agents Actually Come From
Three places to get an RL environment, and they don't compete on the axis you think. The dividing line is where step() runs — a cheap function call or a network trip to a live machine.
5 min
Dynamic Tool Management for Multi-Turn Agents: Only Reasoning Models Can Prune Their Own Toolset
Loading the right MCP tools on demand is a solved problem. Removing the wrong ones over a long conversation is not — and a new benchmark finds that letting the agent do it itself only works if the model reasons.
5 min
DiffusionGemma 26B: A Diffusion LLM Belongs on the Edges of Your Agent, Not the Core
Google open-sourced a text diffusion model that reads documents better than the autoregressive Gemma it's built on — and does multi-step math worse. That split tells you exactly where to wire it in.
5 min
CrewAI 1.14's Pluggable Backends: The Framework Is Un-bundling Its Storage
CrewAI 1.14 lets you swap the default memory, knowledge, RAG, and flow backends for your own. It reads like a config change. It's actually the framework conceding that batteries-included storage was a production liability.
4 min
CoreWeave vs Lambda vs Nebius: How to Actually Pick a GPU Cloud in 2026
The neocloud pitch started as 'cheap raw GPUs vs AWS.' In 2026 the scarce input isn't price — it's powered, networked racks — and the category has quietly split into two businesses that barely compete.
4 min
Claude Science's Reviewer Agent: How to Make Multi-Agent Output Reproducible
Anthropic's new research workbench isn't a smarter model — it's two orthogonal layers, an independent reviewer agent and a reproducibility package, that any agentic pipeline can steal.
4 min
Claude Code Nested Subagents: The Depth Cap Is 5, but Your Token Bill Is the Real Limit
Subagents can now spawn subagents five levels deep. The number that decides whether you should is not the depth — it's how much billed work happens at branches the root never reads.
4 min
BFCL v4 Explained: The Function-Calling Leaderboard Stopped Measuring Function Calling
Berkeley's benchmark made its name scoring whether a model emits the right JSON. Its v4 rewrite puts 70% of the weight on agentic and multi-turn tasks — a quiet admission that single-shot accuracy is solved and no longer predictive.
4 min
Aider Polyglot vs SWE-bench Verified: What Each Coding Benchmark Actually Measures
They look like rival leaderboards for the same question — 'how good is this model at code?' They are not. One grades issue-resolution in Python; the other grades whether a model can emit a correct edit and fix its own mistakes. Pick the wrong one and you ship the wrong agent.
5 min
Agent File (.af): Can You Actually Move a Stateful Agent Between Frameworks?
Letta's .af format serializes an agent's memory, tools, and history into one JSON file. The pitch is portability. What it delivers best is something quieter — a savefile — and that distinction decides whether it's useful to you.
5 min
AG2's v1.0 Rewrite: Why AutoGen's Successor Became an Event Bus
The ground-up Beta that becomes mainline in AG2 1.0 replaces the chatty ConversableAgent with a MemoryStream — a per-channel append-only event log. It's the framework conceding that an agent has to survive its second concurrent user, not just the demo.
4 min
vLLM Is Now a Startup: What Inferact Means for the Inference You Run On
The people who build vLLM raised $150M and became a company. The money isn't the story — who now sets the roadmap of an engine half the industry serves on is.
5 min
TPU vs GPU for LLM Inference in 2026: It Comes Down to the Network, Not the Chip
Per chip, Google's Ironwood and Nvidia's B200 are now within ten percent of each other on every number that used to decide this. The real fork is the interconnect — and vLLM just deleted the reason you couldn't cross it.
6 min
Text Generation Inference Is Archived: Migrating Off TGI in 2026
Hugging Face's TGI went read-only in March. The way it wound down — not the fact that it did — tells you where model serving actually settled.
4 min
EPLB vs LPLB: Why SGLang's 5x MoE Speedup Was a Solver, Not a GPU
SGLang v0.5.14 reports 5x throughput serving DeepSeek-V4 on GB300. The lever isn't Blackwell Ultra — it's a per-batch linear program that reroutes tokens across expert replicas. Static replication plans for the average; no batch looks like the average.
4 min
Prefix-Aware Load Balancing for LLM Inference: Why Round-Robin Wastes Your KV Cache
The load balancer you already trust is the wrong tool for a fleet of inference servers. Spreading requests evenly is exactly what destroys the cache that sets your latency and your bill.
6 min
Optical Context Compression: When It's Cheaper to Show Your Agent a Picture of Its History
DeepSeek-OCR, Glyph, and AgentOCR all render text into images so a vision model can read more with fewer tokens. The compression is real — but a December rebuttal says the honest competitor isn't full text, it's just deleting the old stuff.
5 min
OpenClaw Became GitHub's Most-Starred Project. Then a Fifth of Its Skills Turned Out to Be Malicious.
OpenClaw runs on your own machine, so it feels private and therefore safe. The security crisis of the last three months is a lesson in why those are not the same thing — self-hosting moved the data, not the trust boundary.
5 min