llm

12 articles · newest first

Hand-drawn editorial illustration of a single paper ribbon flowing one way out of a speaker cone toward an open hand, in violet and coral on a near-black background

Your AI chat types its answer word by word. That's SSE, not WebSockets. When you need which

Claude's and OpenAI's APIs stream tokens over server-sent events, a plain HTTP response that never hangs up. Here's when that's all you need, when you really need WebSockets, why polling is fine more often than you'd think, and the proxy and serverless clocks that cut long connections.

Aliteq Team · 3d ago · 13 min

Hand-drawn editorial illustration of a small robot reading a long paper letter, while a tiny coral hand reaches out of the page to steer the robot's hand, on a near-black background

Agents

Your AI agent just read a web page. Who is it obeying now? Prompt injection, explained

Prompt injection is how text your AI reads turns into orders it follows. What direct and indirect injection are, why tools raise the stakes, Simon Willison's lethal trifecta, the defenses OWASP, Anthropic and OpenAI recommend, and their own admission that none of it is a full fix.

Aliteq Team · 3d ago · 11 min

Flat vector illustration of a person in a hoodie sitting cross-legged beside an open filing cabinet drawer of blank documents joined by thin coral lines, on an indigo-violet background

Google's Open Knowledge Format (OKF), Explained: Markdown Files That Agents Can Trust

Google Cloud's new spec for agent knowledge is a folder of markdown files with a few lines of YAML on top. Here is what is in the file, what v0.2 added, and where it differs from a vector index.

Aliteq Team · Oct 3 · 8 min

Hand-drawn editorial illustration of a small chat-bubble robot with a very long questionnaire scroll unrolling from it across a dark page

Security

The AI Questions Enterprise Buyers Ask About Your LLM, With Answer Templates

The vendor review now has an AI tab. The eight things it asks about an app that calls OpenAI or Claude, where each question comes from (SIG, CSA's AI-CAIQ, NIST, ISO 42001, OWASP, the EU AI Act), a fill-in-the-blanks answer for each, and the evidence to attach.

Aliteq Team · Oct 2 · 14 min

Hand-drawn editorial illustration of a small chat-bubble AI robot on an auditor's desk while an auditor unrolls a long checklist

Security

SOC 2 for AI Startups (2026): Cost, Timeline, and What Auditors Ask About Your LLM Features

Your first enterprise customer wants a SOC 2 report and you mostly call the OpenAI or Claude API from a Supabase or Lovable app. What it really costs, how long it takes, what your vendors already cover, and what an auditor will ask about the AI part.

Aliteq Team · Sep 27 · 14 min

Mark Zuckerberg speaking about Meta's AI strategy

meta just promised to open-source the AI model that actually rivals GPT and Claude

Muse Spark 1.2 isn't the laptop-sized model Meta gave away last week — it's the one built to fight Claude Opus 5 and GPT-5.6 head-on, and Zuckerberg just said it's going free too.

Aliteq Team · Aug 13 · 6 min

Meta AI branding on data center server infrastructure, representing the company's open-source AI model push

Meta just open-sourced a 30B AI model that beats Google and Alibaba's best — for free

Muse Glimmer runs on a single consumer GPU and, per Meta's own numbers, beats Gemma4-31B and Qwen3.6-27B at agentic and coding tasks — and Zuckerberg used the release to make his most pointed case yet for open AI over the API-gated kind.

Aliteq Team · Aug 10 · 7 min

A desktop PC with a mid-range graphics card installed, the kind of 8GB hardware this guide is written for

your 8GB graphics card can run real local AI — you're probably picking the wrong model

Phi-4 Mini, Gemma 3, and Llama 3.2 all claim to fit — I checked which one actually leaves room to breathe.

Aliteq Team · Aug 4 · 6 min

rows of server infrastructure representing large-scale cloud computing

Hardware

Qwen3.8-Max open weights (2.4T-A95B): what it takes to run, and the 27B you can actually run

Alibaba put its Max-class model on Hugging Face as Qwen3.8-2.4T-A95B. The download is 2.5 TB in FP8 and the smallest community quant is still 397 GB. Here is the file-size math, the license, and the sibling that fits a 24 GB card.

Aliteq Team · Aug 3 · 8 min

Rows of Nvidia data center GPU servers, representing the AI infrastructure spending Kimi K3's release rattled

China just dropped an AI model so good it erased $590 billion off Nvidia in a day

Kimi K3 is free to download, runs about 70% cheaper than Claude per token, and it just proved open-weight AI doesn't mean second-rate anymore.

Aliteq Team · Aug 1 · 7 min

An AI chat interface running locally on a computer

how to get a free, private ChatGPT alternative that runs entirely on your own computer

You don't need a subscription or an account to have a capable AI assistant. Free, open models running on your own PC give you private, offline, unlimited AI — here's how to set one up.

Aliteq Team · Jul 30 · 9 min

A cloud GPU workstation for fine-tuning AI models

the best cloud GPU for fine-tuning an LLM costs about a dollar — here's the one to rent and why

Fine-tuning sounds expensive until you realize you can rent the perfect GPU for it by the hour. For small models a 4090 does it for pennies; for bigger jobs an A100 is the workhorse. Here's the cheapest path.

Aliteq Team · Jul 28 · 9 min