Tag

#artificialintelligence

367 posts0 followers

Explore Hashnode

Alternatives

My LLM Router Spent 8x More and Matched the Cheap Model Exactly

I built the LLM model routing strategy almost everyone reaches for first: ask the cheap model to answer, have it report how confident it is, and send the question to a stronger model whenever that con

priyanshsinghal.hashnode.dev

jaberadam20013d ago · 11 min read

Your LLM's Explanation Isn't Its Reason: How to Test What Actually Drove the Output

Your scoring pipeline returns JSON. One field is score. The other is reasoning, a neat paragraph that explains the score. It reads well, the team likes it, and someone has started calling it "the audi

simplyexplained.hashnode.dev

Shruti6d ago · 5 min read

From "It Worked Locally" to Azure Cloud Reality: My Hackathon War Stories, Blunders, and Cloud Architecture Epiphanies

The Spark: What We Set Out to Build Our plan sounded incredible on paper: build an AI-Powered Content Authoring Platform on Microsoft Azure that turns half-baked bullet points and rough ideas into str

shipnshatter.hashnode.dev

ZyVOPOct 11 · 11 min read

OpenAI’s Math: Fast Generation, Slow Verification

OpenAI's math release has been public since October 6. The first bill for checking it has already arrived. Open github.com/openai/math and the first thing you notice is what's missing: no benchmark ha

blog.zyvop.com

Mira roySep 23 · 6 min read

Scoping Tool Permissions for AI Agents: A Practical Pattern

AI agents introduce a security problem that ordinary chatbots do not: they can take actions. A chatbot might generate a bad answer. An agent connected to tools can read files, update records, call API

3 ainetwork.hashnode.dev

Kushal RSep 20 · 2 min read

Jev: The AI Model That Doesn't Talk, It Just Decides

So, yesterday I was doomscrolling YouTube and just saw a video byHarkirat Singh. This video was about the new System One Model Jev. After watching that video, I thought of putting my thoughts on it. S

kushalr.hashnode.dev

8080AISep 18 · 8 min read

Why AI Coding Tools Get Multi-Tenant Isolation Wrong

Multi-tenant SaaS has a well-understood security model: scope every query to a tenant, enforce it at the data layer, and test the horizontal access paths until you're confident one customer can never

8080ai.hashnode.dev

GeekyAntsSep 17 · 10 min read

From Manual Testing to AI-Assisted Automation with Playwright Agents

For years, automation engineers have followed a familiar rhythm. Requirements come in, test cases are written, scripts are automated, locators break, scripts fail, and debugging begins. Fix, re-run, r

techblog.geekyants.com

Joselo MartinezSep 16 · 4 min read

Agentic AI Beyond the Hype: Why the Boundaries Are Key in Deterministic and Non-Deterministic Behavior for Agents

Let’s imagine we are implementing deterministic behavior for agent systems using control techniques (harnessing). Suddenly, we observe that the agent's actions and responses begin to become clumsy, an

2 designednotmagic.hashnode.dev

Doogal SimpsonSep 14 · 5 min read

Optimize Cheap LLMs for Frontier-Level Accuracy

You don't always need expensive frontier LLMs to achieve production-grade results. By investing in context engineering, structured tool access, and strict guardrails, you can optimize cheap utility mo

doogal.dev

Search Hashnode

Explore Hashnode

Trending tags this week

My LLM Router Spent 8x More and Matched the Cheap Model Exactly

Your LLM's Explanation Isn't Its Reason: How to Test What Actually Drove the Output

From "It Worked Locally" to Azure Cloud Reality: My Hackathon War Stories, Blunders, and Cloud Architecture Epiphanies

OpenAI’s Math: Fast Generation, Slow Verification

Scoping Tool Permissions for AI Agents: A Practical Pattern

Jev: The AI Model That Doesn't Talk, It Just Decides

Why AI Coding Tools Get Multi-Tenant Isolation Wrong

From Manual Testing to AI-Assisted Automation with Playwright Agents

Agentic AI Beyond the Hype: Why the Boundaries Are Key in Deterministic and Non-Deterministic Behavior for Agents

Optimize Cheap LLMs for Frontier-Level Accuracy