PastAGI

Practical AI guides, honest tool reviews, engineering deep dives, real-world use cases, and sharp analysis that cuts through the hype.

Recent

TontaubeV1 review with reproducible VRAM and latency math for running a 2.9B open-weight text-to-speech model locally.

Tools • Sep 01, 2026 •12 min read

TontaubeV1 Review With Serving Math You Can Run

This TontaubeV1 review audits the 2.9B character-level TTS model with serving math builders can verify, covering VRAM, latency, and long-form narration.

#tts #local-inference +4

How the ChatGPT DSA designation brings AI chat interfaces with web search under EU search engine rules.

News • Aug 31, 2026 •11 min read

ChatGPT DSA Designation Sweeps In Every AI Search Engine

The ChatGPT DSA designation reportedly makes it the EU's first AI-native very large online search engine. Here is the test deciding which AI tools follow.

#dsa #chatgpt +3

This oMLX review tests whether a Mac local LLM server really cuts agent wait times from 90 seconds to 5.

Tools • Aug 30, 2026 •11 min read

oMLX Review, Auditing the 90s to 5s Agent Claim

This oMLX review audits the 90s to 5s agent latency claim, shows where wait time goes on Apple Silicon, and gives you a benchmark to run on your Mac.

#omlx #apple-silicon +4

NLP vs LLM vs RAG branches routed by task shape and cost, the decision framework that determines where document workloads land.

Guides • Aug 29, 2026 •12 min read

NLP vs LLM vs RAG, Routed by Task Shape and Cost

NLP vs LLM vs RAG is a routing decision set by task shape. Compare the cost math, failure modes, and an LLM-fallback pattern before picking a model.

#classical-nlp #rag +4

The reported NVIDIA Hugging Face acquisition would put the leading open weights hub under the vendor that supplies most AI accelerators.

News • Aug 28, 2026 •12 min read

NVIDIA Hugging Face Acquisition Ends the Neutral Hub

The NVIDIA Hugging Face acquisition turns the Hub into vendor infrastructure. Here is how builders mirror weights, pin revisions, and cut lock-in.

#nvidia #hugging-face +3

Text-to-SQL evaluation tests whether AI-generated SQL returns defensible answers on real warehouse data instead of just matching public benchmark scores.

Engineering • Aug 27, 2026 •12 min read

Text-to-SQL Evaluation That Catches Silent Wrong Answers

Public benchmarks say 89%, your warehouse says otherwise. Build a text-to-SQL evaluation with schema-specific oracles that catches silent wrong answers.

#text-to-sql #nl2sql +4

A GPU cluster in a data center represents the hardware baseline behind MoE serving cost, where residency, communication, and utilization set the real invoice for a sparse model.

Engineering • Aug 26, 2026 •12 min read

MoE Serving Cost Math for 6 of 125B Active Parameters

MoE serving cost for a 6-of-125B model is not 6B per token. All 125B stay in VRAM, so run the builder math on residency, routing, and break-even.

#moe #inference-cost +4

AI agent memory depends on layered persistent stores rather than raw context windows to retain recruiter preferences and candidate history across sessions.

Use Cases • Aug 25, 2026 •12 min read

AI Agent Memory Lessons From LinkedIn's Hiring Assistant

AI agent memory lessons from LinkedIn's hiring assistant. This four-layer teardown covers token payback math, decay rules, and privacy classes to copy.

#agent-memory #ai-agents +3

Speculative decoding turns idle CPU compute into nearly four times faster token generation for large language model inference.

Engineering • Aug 24, 2026 •11 min read

Why Speculative Decoding Pays Nearly 4x on CPUs

Speculative decoding turns idle CPU cores into 4x faster LLM generation. Learn why it works, when gains collapse, and when CPU beats GPU or API.

#speculative-decoding #cpu-inference +3

AI agent token usage overtaking human-driven traffic on LLM API gateways and reshaping how platforms meter, price, and serve machine callers.

News • Aug 23, 2026 •11 min read

AI Agent Token Usage Overtook Humans on OpenRouter

OpenRouter data shows AI agent token usage passed human traffic on February 6, 2025, with 14x growth and ~70 percent cached. Here is how to audit your mix.

#ai-agents #token-usage +4

WhatsApp Scam Alert flags scam patterns on the phone itself while message content remains unreadable to servers under end-to-end encryption.

Use Cases • Aug 22, 2026 •12 min read

How WhatsApp Scam Alert Detects Scams It Cannot Read

WhatsApp Scam Alert flags scams without Meta reading your messages. See how on-device AI works under end-to-end encryption and how to copy the pattern.

#whatsapp #on-device-ai +4

A teardown of Stampli's AI-assisted product launch claim, examining what the 68% launch-hour reduction measures and the conditions that made it possible.

Use Cases • Aug 21, 2026 •10 min read

AI-Assisted Product Launch Teardown of Stampli's 68% Claim

A builder's teardown of Stampli's 68% launch hour cut with Codex and ChatGPT, and the AI-assisted product launch workflow your team can copy.

#codex #chatgpt +4