ClickHouse Bought Langfuse: What It Means for Your LLM Traces — and Whether It Stays Open Source
A database company acquiring an observability startup looks like a tooling deal. It isn't. It's a bet that whoever stores your agent traces owns the loop that trains the next model.
4 min
Claude Sonnet 5's Tokenizer Tax: Why the Same Rate Card Costs More Per Task
Sonnet 5's rate card matches Sonnet 4.6's — $3/$15 per million tokens. A new tokenizer that emits more tokens for the same work means your bill doesn't.
3 min
Claude Code Agent Teams vs Subagents: When Your Workers Need to Talk to Each Other
Claude Code's new experimental Agent Teams let parallel sessions message each other and share a task list. The real question isn't 'do I want parallelism' — subagents already give you that — it's whether your workers need to disagree.
5 min
Localhost Stopped Being a Trust Boundary the Moment Your Agent Started Browsing
Microsoft's AutoJack shows how a single web page can RCE the host running an AI agent — not by forging an origin, but because the agent's own browser is localhost.
5 min
Mem0 vs Zep vs Letta: Why Agent-Memory Benchmarks Don't Agree
The whole agent-memory leaderboard war — 84% vs 58% vs 75% — is being fought over a ten-conversation dataset called LOCOMO. Once you see how the numbers are made, you stop shopping on accuracy.
4 min
Agents' Last Exam: Frontier Agents Pass 2.6% of Hard Professional Work — and the 2.6% Is the Point
Berkeley's ALE scores whole deliverables, all-or-nothing, the way a client would. That single methodology choice is why the number is 2.6% and not the 90s vendors keep quoting.
4 min
Agentic Resource Discovery (ARD): The Search Layer That Sits in Front of MCP and A2A
Eleven vendors just agreed on how agents find tools across the open web. The interesting part is what ARD refuses to be — not a protocol, not a registry of record, just the step before invocation.
5 min
Do AI Agents Self-Correct? Why Reflexion Works and 'Check Your Work' Backfires
Telling an agent to review its own reasoning usually makes it worse, not better — and the reason it fails is the same reason Reflexion succeeds. Both come down to one asymmetry: verifying is only easier than generating when the verifier knows something the generator doesn't.
5 min
Agent Registry vs MCP Registry: The New Discovery Layer, and Why It's Already Fragmenting
The MCP registry catalogs tools. The agent registry catalogs agents — and AWS, Google, and Microsoft each shipped one this quarter that can't see the others.
3 min
Agent Client Protocol (ACP): The Third Protocol Named ACP, and Why It's LSP for Coding Agents
MCP gives an agent tools. ACP gives an agent an editor. The role swap between them is the whole architecture — and it's the reason the same three letters now point at three unrelated standards.
4 min
Zero Trust for AI Agents: Why the New Frameworks Treat Your Agent as an Insider Threat
Anthropic and Google DeepMind converged on the same uncomfortable premise in 2026: the agent already has legitimate credentials, so the honest security model assumes it's compromised and bounds what it can do — not whether it can get in.
4 min
vLLM vs SGLang vs LMDeploy: Picking a Self-Hosted Inference Engine in 2026
With TGI archived and Hugging Face pointing everyone at vLLM and SGLang, the open-source serving field narrowed to three real choices. They hit nearly the same throughput ceiling from opposite directions — so speed is not the thing you're actually picking.
4 min
Text-to-SQL Accuracy in 2026: Why the Benchmark Says 90% and Your Warehouse Says 40%
Top systems clear 90% on academic SQL benchmarks and 30–60% on real enterprise warehouses. The gap isn't the model's syntax — it's your schema. And the leaderboards are half wrong.
4 min
Stainless Is Winding Down: Where to Generate SDKs and MCP Servers Now
The two best independent SDK generators got bought in 2026 — Fern by Postman, Stainless by Anthropic, which is retiring its shared generator. The layer that turns an API into agent-usable tools stopped being neutral infrastructure.
4 min
Faithfulness vs Groundedness vs Correctness: Which RAG Hallucination Check Catches a Wrong Answer
A faithfulness score of 1.0 doesn't mean your RAG answer is right. It means the model didn't stray from the context — even when the context was wrong. Here's what each check actually audits.
4 min
The Best Small Model for Your Agent Isn't the Smallest — or the Smartest
Qwen3-4B, Phi-4-mini, Gemma, Nemotron 3 Nano: the pick forks on a question no leaderboard prints — are you short on memory or short on tokens-per-dollar? And the score that decides an agent isn't MMLU.
4 min
Pydantic AI V2 Is Out: What 'Capabilities' and the Harness Actually Change
V2 went stable on June 23 after seven betas, then shipped four releases in nine days. The real news isn't the version bump — it's a bet that the winning agent abstraction is a harness, not a graph.
5 min
Pi's System Prompt Is Under 1,000 Tokens: The Case Against Heavy Coding-Agent Harnesses
Most coding agents open with a ~10,000-token system prompt. Pi opens with under 1,000 and lets the model write its own tools. The bet underneath: the model already knows how to be an agent, and every instruction token is a task token you don't get back.
4 min
The NSA's MCP Security Guidance: The First Advice That Defends Against Your Own Agent
The NSA's Security Design Considerations for MCP reads like every other threat list until you notice its signature control points the wrong way — at the outbound wire, not the untrusted server. That inversion is the whole document.
5 min
MiniMax M3: Frontier Coding and 1M Context on Open Weights — Read the Latency, Not the Leaderboard
M3 claims to beat GPT-5.5 on SWE-bench Pro while running weights you can host yourself. The benchmark row is the least trustworthy thing in the release — and the architecture is the most.
5 min
MCP Is Deprecating Sampling, Roots, and Logging: What the 2026-07-28 Spec Cuts and Why
The stateless rewrite got the headlines, but the quieter change is the one that tells you what MCP has decided to be. Three original primitives are on the way out — and they're the exact three where the server reached back into your runtime.
5 min
MCP's Stateless Spec Fixes Session Hijacking — and Hands You Three New Attack Surfaces
The 2026-07-28 revision closes the holes the protocol used to own. The same three headline features quietly relocate the security burden onto server code that mostly doesn't exist yet.
5 min
The Mastra npm Attack: AI Agent Frameworks Are the New Supply-Chain Target
A North Korean crew republished 140+ Mastra packages in 88 minutes with a poisoned dependency. The scary part isn't the payload — it's that the whole attack ran before any of your agent's guardrails woke up.
5 min
LLM Cascade vs Router: Escalate to a Bigger Model, or Route Around It?
A router picks a model before it sees the answer; a cascade tries the cheap one first and escalates only if a judge says so — and that judge, not the models, decides whether you actually save.
6 min
Interleaved Thinking: When Should an AI Agent Reason Between Tool Calls?
The point of thinking between tool calls isn't a smarter first plan — a model can plan up front without it. The point is that the model can notice a tool returned something wrong and re-plan on the spot, instead of barreling ahead.
4 min
How to Enforce a Token Budget on an AI Agent (Not Just Measure It)
Most 'agent budgets' are alerts wearing a brake's uniform: they tell you after the money is gone. Real enforcement is a prediction problem, because the cost of the next step is a bound you can only ever estimate — never a number you can look up.
5 min
How MCP Servers Actually Ship: The Registry Is a Phone Book, OCI Is the Supply Chain
The official MCP registry deliberately refuses to host code — so the hard part, trust, lands wherever the artifact lives. Docker's answer is to make that place an OCI image.
4 min
Google Open-Sourced an Agent Memory System With No Vector Database. Read the Design.
A Google PM's 'Always On Memory Agent' stores everything in SQLite and consolidates it with an LLM every 30 minutes. The 30-minute number tells you exactly what it's for — and what it isn't.
5 min
Does Structured Output Hurt LLM Accuracy? The Format Tax, Measured
Forcing JSON can cost a reasoning model 10–15% — but the tax is paid during thinking, not from structure itself. The fix is where you put the reasoning, not whether you constrain.
4 min
Claude Sonnet 5 vs Opus 4.8 for Agents: The Cheaper Model and the Tokenizer Catch
Sonnet 5 lands at 40% below Opus and beats it on terminal work — but a new tokenizer quietly inflates every token count by ~30%, so the rate card is not the price. Do the cost math in your own units.
5 min