The MCP debate has a context problem
Every few months, a new technology gets its premature obituary. Across many developer circles, MCP’s has already been written. Too The post The …
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
Where AI saves me time and where it slows me down
I use AI every day, and I would not want to go back. That is probably the simplest way to The post Where AI saves me time and where it slows me down a…
APIs aren’t dead. Here’s where MCP fits alongside them.
The allure of emerging technology is undeniable, but adopting it rarely means completely ripping out what already works. Instead, new The post APIs ar…
How async processing hides latency and improves responsiveness
Editor’s Note: This article contains an exclusive excerpt from Latency by Pekka Engberg, which helps readers diagnose latency problems and The post Ho…
85% say code review is the new bottleneck. Here’s what the AI coding narrative leaves out.
A merge is a contract. The moment a change lands on main, every other team in the organization starts building The post 85% say code review is the new…
The impressive AI demo is dead. Here’s what actually reaches production
Most engineering teams I talk to can ship an AI demo. The prototype works, stakeholders are impressed, and everyone agrees The post The impressive AI …
Why retrieval quality is becoming the defining challenge in AI agent architecture
Agentic systems usually have two jobs: Build context, then use that context to produce an answer or action. Many failures The post Why retrieval quali…
What running Kubernetes across millions of clusters taught AWS about zone failures
Handling the obvious failures is the easy part: a server goes down, you spin up another. The failures that actually The post What running Kubernetes a…
The “silent hallucination” loop: how our autonomous data pipeline poisoned its own vector store
Nothing matches the dread of checking a perfectly green observability dashboard with sub-100ms latency, right before an enterprise client emails The p…
The organizational iceberg: the invisible data breaking your AI agents
When building data platforms for large institutions, we often make decisions based on what we can see, ignoring blind spots, The post The organization…
How to kill the code review
This is a follow-up to “How long before we stop reading the code?“, which argued that traditional code review is The post How to kill the …
Your social login buttons run on third-party cookies. FedCM doesn’t.
“Sign in with Google” and “Continue with Apple” have carried federated login for more than a decade. They strip away The post Your social login button…
Why traditional CI/CD fails for LLMs (and the release gates we built to fix it)
This article explains why traditional CI/CD gates are not enough for production AI systems. I share a practical release-gating approach The post Why t…
The call is coming from inside your pipeline: the anatomy of a Codecov attack
In January 2021, an attacker added a single line of code to a popular bash script. Tens of thousands of The post The call is coming from inside your p…
Operating Kubernetes at scale: a few stories from running Amazon EKS
Amazon EKS runs hundreds of thousands of Kubernetes clusters across more than thirty AWS regions. Operating at that scale has The post Operating Kuber…
Greptile, Cursor, and Devin agree that agents should run their code. What they run it against matters.
The industry has recognized that shipping agent code at scale requires runtime verification, and it is moving that way fast. The post Greptile, Cursor…
Your engineering org needs an AI slop registry
AI coding tools don’t just help engineers write code faster. They help engineers make the same mistake faster, at scale, The post Your engineeri…
The AI agent identity problem nobody’s talking about
Many agentic projects can sail through development just fine. Then they hit security review — and that’s where things can The post The AI …
Template-based data extraction is dead. Here’s what comes next.
Modern businesses are in a constant, uphill battle against what to do with unstructured data: PDFs, contracts, scanned images, customer The post Templ…
How we cut AI costs by 80%
AI costs are rising, and not for the reason most people assume. It’s true that the models are getting more The post How we cut AI costs by 80% appeare…
Agent Toolkit for AWS includes 20+ agent skills, but your agent might not load them without this one file
If you’re like me, sometimes you get so excited to try something new that you don’t read the docs all The post Agent Toolkit for AWS includes 20+ agen…
AI can write the code. Your team still owns the debt.
The software industry is still talking about AI mostly in terms of speed. Models and agents can now generate code The post AI can write the code. Your…
GitLab just surveyed 1,500 developers. Here’s why it matters for your codebase.
For the past two years, the conversation about AI-assisted software development has been dominated by speed. A new GitLab survey The post GitLab just …
Your agent wants to search like a 2010 quant
AI agents need the right information to work well. Whether they manage to find it is the difference between success The post Your agent wants to searc…
“I think this is costing us more than we realize”: what permissionless ownership really asks of you
Most people do not stay quiet because they have nothing to say. They stay quiet because speaking up changes their The post “I think this is cost…
The database storage problem is solved. Here’s what comes next.
For most of its 30-year history, Postgres has been viewed as a transactional database. Organizations trust it with customer records, The post The data…
Your AI pipeline is broken, and your dashboards don’t know it
Recently, a crucial RAG pipeline used by one of our corporate clients began hallucinating about financial numbers without notifying us The post Your A…
Code is a message to the future
Engineers communicate constantly. Slack messages, design docs, RFC threads, code review comments: the job is as much about sharing intent The post Cod…
What your logs can’t tell you when an AI agent acts alone
For a long time, logs lived in a strange purgatory: technically required, rarely read, and mostly forgotten until something broke. The post What your …
PagerDuty’s CAIO says most AI incident tools are missing a critical layer
AI is empowering software teams to ship code faster than ever. Given that an average of 70% of incidents stem The post PagerDuty’s CAIO says mos…