Treat Per-Task Model Switching as a Concurrency Protocol
Changing the model for a running AI task is not a settings update. It is a distributed operation: read current task -> prepare credentials/config -…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
claude
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
Service Level Objectives for Complex Microservices
Why SLOs Break in Microservices A SLO that works for a monolith often collapses when you distribute the same logic across 30 services. The math of ava…
Building a Culture of Reliability: Beyond the SRE Handbook
You Can't Hire Your Way to Reliability I've seen companies hire 5 SREs and expect reliability to magically improve. It doesn't. Reliability is a cultu…
The 10 Most Expensive Software Failures in History — and the One Thing They Share
The biggest losses in software history were, with one deliberate exception, not attacks. They were silent, correlated, self-inflicted — and they teach…
Escalation Policies: How to Route Alerts Without Waking Everyone
A misconfigured escalation policy has two failure modes, and both are bad. Either every engineer on the team gets paged for a minor hiccup, or nobody …
On-Call Engineer Burnout: How to Build Sustainable Rotations
Most on-call rotations start with good intentions and end with someone updating their LinkedIn. The schedule ships as a shared Google Sheet, the team …
We Published the First Formal Conformance Standard for AI Agents
We audited 8,000+ real API calls across multiple providers and fault scenarios. The results exposed a systemic blind spot in how the industry handles …
The Pod That Lied: A Kubernetes Readiness Probe War Story
Last time I told you to bring coffee. I did. This one didn't start at 2 a.m. — it started at 10:40 on a perfectly ordinary Tuesday, which, if anything…
I Run 1,000 Agents in Production. Here's What I Learned About Reliability
The 3 AM Wake-Up Call Last month, my phone buzzed at 3:17 AM. A Slack alert informed me that my OpenAI bill had jumped from $47 to $5,847 in 58 minute…
Why Your Microservices Need Circuit Breakers (And How to Add Them)
The Cascading Failure That Took Down Everything Our payment service went down for 3 minutes. No big deal, right? Except every service that called paym…
Your Guardrails Are a Firewall. Your Failures Are a Cascade
TL;DR— Most production AI teams build safety layers using the content-moderation mental model: classify input, classify output, block or pass. But the…
SLOs That Product Managers Actually Understand
The SLO Translation Problem You define an SLO: 99.95% availability with p99 latency under 200ms. Engineering loves it. Product managers glaze over. Th…
An AI agent design that refuses to act on what it merely assumes
LedgerAgent is a design that forces AI agents to verify every state change before recording it as true, and to check every consequential action agains…
SLO as Code — нельзя верить людям
Всем привет, меня зовут Вячеслав, я Team Lead SRE в Купере. Рассказ в этой статье пойдет о том, как мы внедряли SLO , чего достигли и какие лайфхаки н…
Exponential backoff with jitter stopped our CI retry storms
TL;DR: Exponential backoff with jitter spreads client retries over time so a recovering service doesn't get flattened by a synchronised wave. We added…
Ваши постмортемы — это поминки. И добрая половина процессов в компании тоже
Однажды я зашёл в компанию через неделю после крупного падения и попросил показать постмортем. Мне показали — с гордостью. Таймлайн поминутно, five wh…
Choosing Your First SLI: A Decision Framework for New SRE Teams
New SRE teams ask the same question: what should we measure first? The temptation is to track everything CPU, memory, latency, error rate, queue depth…
Pramaana Labs raises $27M seed round from Khosla Ventures to bring formal verification to AI
Pramaana will focus on highly sensitive verticals like law, drug discovery, and tax preparation — where errors can be costly and reliability is at a p…
Your MCP Agent is Logging "Sucess: true" While the task never ran
You build an agent. It calls an MCP tool, gets a response, logs success: true, and moves on. Thirty-three minutes later a customer emails asking why t…
Surviving the region you run in: failover on Aurora DSQL, and what the demo proves
The thesis Quorum is built on is uncomfortable and true: the tools a team uses to coordinate an incident often live in the same region as the thing th…
Sliding-Window Spend Guard: the $47K Loop Per-Call Caps Miss
Sliding-Window Spend Guard for AI Agents: Catch the $47K Loop Per-Call Caps Miss A sliding-window spend guard sums what your agent has spent over the …
Model Selection for Weibull Series Systems: When Simpler Models Suffice
When can you safely use a simpler model for a series system? I ran extensive simulation studies with likelihood ratio tests to get a quantitative answ…
The Economics of Reliability: When to Invest, When to Accept Risk
Reliability is not a virtue. It's an investment. Too little and you lose customers. Too much and you can't afford to ship. The question is: where's th…
Your Scraper Died at Row 12,000. The Rerun Pattern.
My scraper died at row 12,000 of 50,000, three hours in. The crash itself was cheap. A process gets OOM-killed, a quota trips, a machine reboots, it h…
Railway vs Fly.io: I Wanted More Control After Railway’s May 2026 Outage
TL;DR I no longer recommend Railway for serious production workloads after its recent pattern of incidents. Fly.io is not simpler, but it is one of th…
Why We Restart to Fix It
On Second Thought — Episode 10 The pager has gone off. Memory on the auth service is climbing in a way it should not be. You SSH in, you observe nothi…
The Fire That Reached the Backups: The OVHcloud Strasbourg Data-Centre Fire, 2021
Tales from the Bare Metal — Episode 05 In the early hours of 10 March 2021, a fire began in a power room in Strasbourg. By morning an entire data cent…
Claude Code for Canary Deployments: How I Ship to 1% of Users Before Breaking Everything
I used to ship by faith. The change passed code review, the tests went green, the deploy button was right there, and I pressed it. Most of the time it…
Grafana 'No Data' after migration: 7 reconcilers we had to kill first
The first fix lasted 90 seconds. We had corrected the Grafana datasource URL from prometheus:9999 back to prometheus:9090, watched the pod roll, refre…
What SSL Error Means and How to Fix It
An SSL error means your browser or HTTP client could not complete the TLS handshake with the server. The connection was dropped before any data was ex…