Tag feed

#llm

5,259 posts298 followers

Trending tags this week

I Handed Claude Code the Keys. Turns Out I'm Not the Only One Using Them.

13h ago · 11 min read · Two months ago I handed Claude Code the keys to a fresh VM and walked away to see what it would break. It broke a few things, and every one of them was mine to break -- my VM, my config, my time. I wr

JJoel commented

SKSathvic Kollusathvickollu.hashnode.dev

0

How much VRAM do you actually need to run Llama 3 or Gemma locally?

5h ago · 6 min read · Every few days someone in a local LLM thread asks the same question: "will this run on my 3060?" And the answers are almost always vibes. "Should be fine." "Probably need to quantize." Nobody shows th

Join discussion

DGDeepak Goyalblog.deepakgoyal.ai

0

Your LLM Reviewer Agrees With Itself. That's the Bug.

1d ago · 7 min read · When one LLM generates content and another from the same family reviews it, they can agree completely — and both be wrong in the same direction. That's not a capability failure. It's family bias: a st

Join discussion

RRaplsraplsworks.hashnode.dev

0

Before you disconnect MCP servers, read the context breakdown

10h ago · 4 min read · When an AI coding agent starts drifting mid-session, forgetting a constraint, repeating a solved question, giving thinner answers than it did an hour ago, the temptation is to reach for the explanatio

Join discussion

AJAlen Joypragmaticstack.in

0

More Agents, More Problems

1d ago · 14 min read · 🗓️ Last updated: June 2026 Multiagent systems get pitched as the next leap in agentic capability. Single agent struggling with a long task? Add a planner. Reasoning is shallow? Add a critic. Output

Join discussion

АСАлексей Спиновspinov001.hashnode.dev

0

The HTTP Code Your AI Agent Doesn't Handle Yet: 402

17h ago · 15 min read · Your fetch agent knows two endings to a request. 200: parse it. 403: back off, rotate, or skip. That branch has been the whole game for years. There's a third ending now, and it's the one your code fa

Join discussion

MAMajid Allahverdidevwithmj.com

0

Skills.sh Is the npm Moment for AI Agents (And Most Developers Haven't Noticed)

20h ago · 7 min read · I started building AI agents about two years ago. Not toy demos, actual production features inside a health-tech product. And every single project started the same way. Write the tool-calling wrapper.

Join discussion

Jjasmineparkjas-blogs.hashnode.dev

0

We put a cost SLO on our LLM features. It is the number that finally made eng care about token spend.

22h ago · 3 min read · TL;DR: Our LLM bill was a single number going up, and "spend rose 18%" is not something an engineer can act on. We gave each feature a cost SLO, a target cost per successful outcome with a monthly err

Join discussion

SCSuny Choudharylangprotect.hashnode.dev

0

AI-SPM vs CSPM: What’s the Difference and Why Enterprises Need Both

1d ago · 5 min read · CSPM helped security teams understand where cloud infrastructure was exposed. But AI introduced a different problem. Now enterprises do not only need to know whether a storage bucket is public or an I

Join discussion

AGAnand Guptablog.altimate.ai

0

You Are the Trust Layer

1d ago · 5 min read · Sometime this year your job changed, and nobody sent the memo. You used to write code. Now you mostly approve it: you read a summary, it looks right, you hit accept, and you've moved on before you cou

Join discussion

#llm

Search Hashnode

#llm

Trending tags this week

I Handed Claude Code the Keys. Turns Out I'm Not the Only One Using Them.

How much VRAM do you actually need to run Llama 3 or Gemma locally?

Your LLM Reviewer Agrees With Itself. That's the Bug.

Before you disconnect MCP servers, read the context breakdown

More Agents, More Problems

The HTTP Code Your AI Agent Doesn't Handle Yet: 402

Skills.sh Is the npm Moment for AI Agents (And Most Developers Haven't Noticed)

We put a cost SLO on our LLM features. It is the number that finally made eng care about token spend.

AI-SPM vs CSPM: What’s the Difference and Why Enterprises Need Both

You Are the Trust Layer