TSMC, Intel supplier Qnity bets on local production to win business
TAIPEI --The CEO of Qnity, a leading supplier of semiconductor chemicals and materials, says a "local-for-local" strategy, including sourcing more tha
Nikkei Asia Tech1 min read
production
22 stories
U.S. Manufacturing Activity Sustains Growth in September as Backlogs Surge
Manufacturing maintains nine-month growth streak despite soaring costs and trade barriers. The post U.S. Manufacturing Activity Sustains Growth in September as Backlogs Surge appeared first on EE Times.
EE Times6 min read
Robotics companies turn to rush 3D printing as demand for faster production grows
Upside Parts, a Massachusetts-based custom manufacturing company, released an analysis of more than 30,000 3D-printed parts produced across hundreds of customer orders, looking at how robotics companies use on-demand 3D printing. Robotics customers accounted for 82.3 percent of total part volume.
Robotics & Automation News3 min read
Honda delays next-gen CR-V hybrid production several months in US, Canada
NEW YORK -- Honda Motor will push back mass production of its next-generation hybrid vehicles in North America by several months, Nikkei has learned.P
Nikkei Asia Tech1 min read
Honda pauses Bangkok motorcycle production due to flooding
BANGKOK -- Honda Motor paused production at its Bangkok motorcycle plant Monday amid heavy rains since late last week that have caused problems for a
Nikkei Asia Tech1 min read
How to Reduce LLM Token Costs in Long Conversations: What Caching Saves, and Where It Stops
A long conversation costs far more than its number of turns suggests, because every request carries the system prompt and the entire history again, so total input grows with the square of the number of turns.
Maximem Synap Blog13 min read
Claude API Pricing in 2026: Every Model per Million Tokens, and What Pro and Max Cost
The Claude API costs between $1 and $10 per million input tokens and between $5 and $50 per million output tokens on Anthropic's current models.
Maximem Synap Blog14 min readWhat is prompt injection? The 3 attack surfaces to fix
Prompt injection hijacks your LLM via user input, retrieved docs, and tool results. Three attack surfaces, and the defenses that actually work in production.
LLMTest Blog7 min readLLM cost per user in 2026: $0.15–$0.73 across three workloads
Per-user LLM cost at 1,000 daily users in 2026: token math across chat, extraction, and RAG at two model tiers, with break-even math for solo devs.
LLMTest Blog5 min readLLM hallucinations explained: causes, types, production fixes
Why LLMs hallucinate, the three error types, prompting patterns that reduce them, and the one production eval that catches failures before your users see them.
LLMTest Blog6 min readLLM conversation costs in production 2026: $50/day without compaction
Per-session cost math for 1,000 daily LLM chat sessions at three model tiers. Why stateless APIs compound costs and when sliding-window compaction pays off.
LLMTest Blog5 min readHow to manage LLM context windows in production: 3 Node.js patterns
Sliding window, summarization compaction, priority truncation: three Node.js patterns for managing context in long-running LLM conversations.
LLMTest Blog5 min readSystem prompt explained: behavior, cost, and pitfalls
A system prompt is the hidden instruction block that shapes every LLM response. Here's how it works, what it costs, and the production pitfalls to avoid.
LLMTest Blog6 min read
Product Evals in Three Simple Steps
Label some data, align LLM-evaluators, and run the eval harness with each change.
Eugene Yan9 min read
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models.
Eugene Yan1 min read
NVIDIA GTC 2025 - Building LLM-Powered Applications
Chip Huyen and I share what we've learned, best practices, and insights at NVIDIA GTC 2025.
Eugene Yan1 min read
Running Deep-Agent in Production: Lessons from the Trenches
Deep agents aren't like simple chat applications. A single task might make 10-50+ LLM calls, take minutes, and cost $1-10+. Here's what I wish I knew from day one about running them in production.
Oats Blog4 min read
39 Lessons on Building ML Systems, Scaling, Execution, and More
ML systems, production & scaling, execution & collaboration, building for users, conference etiquette.
Eugene Yan9 min read
Showing 18 of 22 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts