Tech Big Bang
Daily digest of yesterday's top tech news and highlights
π PrimeSkills LiveVisit β
β‘Solo Founder Β· Independent Creator
Hi, I'mDongqi Chen
Building Interesting Things Here
10+ years in automotive systems, AI application explorer, indie developer. Sharing hands-on experience in in-vehicle development, AI engineering, and team management, while incubating small but beautiful products.
CarOSAI/LLMIndie Hacker
BLOG
Latest Articles
Technical articles, tutorials, and insights covering automotive dev, AI engineering, and team management
LLMAutomated TestingAI Engineering
LLM-Driven Automated Testing Series (14): Production Engineering β Why Testing Turns Out to Be the Cheapest Line Item in This Whole Series
A code-generation workflow I documented earlier burned thousands of dollars in tokens during debugging. The testing scenarios verified across this series β AutoRestTest testing a 15-operation API for about a dime, pytest-triage capping itself at 10 model calls per run by default β are off by orders of magnitude. This article puts the evidence from 13 prior articles side by side to answer the three questions the planning doc left for last: why testing-scenario cost is what it is, where the human-in-the-loop gate actually belongs, and which scenarios should explicitly avoid LLMs altogether.
Β·12 min
LLMAutomated TestingFlaky Test
LLM-Driven Automated Testing Series (13): Flaky Tests Aren't a Rerun-Count Problem, They're a Classification Problem
pytest-rerunfailures (477 stars) and flaky (397 stars) handle test instability with the same one-liner: if it fails, rerun it a few times. That doesn't answer what the planning doc actually asks β was this failure a real bug, environment jitter, or a badly designed test? The only project actually attempting that root-cause classification with an LLM is a 2-star, less-than-two-months-old repo called pytest-triage β and its most instructive feature turns out to be the four safety invariants it wraps around AI judgment, guaranteeing AI is never allowed to affect whether a test actually passes or fails.
Β·11 min
LLMAutomated TestingVisual Regression
LLM-Driven Automated Testing Series (12): Beyond Pixel Diffs β Who's Actually Making LLMs 'Understand' UI Changes
BackstopJS, at 7.2k stars, handles rendering noise with exactly four numeric config knobs β misMatchThreshold, requireSameDimensions, ignoreAntialiasing, usePreciseMatching β which is still just fighting font-rendering jitter with pixel-level tolerance. The project that actually wires a VLM/LLM into the visual-regression judgment loop is a 23-star repo called vlmkit, whose own internal benchmark notes state outright that one model hallucinates red into red. Putting these two side by side answers, concretely, what semantic visual regression actually solves β and what new problems it introduces.
Β·12 min
LLMAutomated TestingAPI Testing
LLM-Driven Automated Testing Series (11): Why API Testing Is Actually the Most Conservative Battleground for LLMs
Keploy has 18.5k stars and its README says 'Expand API Coverage using AI' β but grep the entire open-source Go codebase for LLM/AI keywords and you'll find zero implementation code. Schemathesis, at 3.6k stars, uses no LLM at all β it finds real server 500 errors purely through Hypothesis-based property-based fuzzing. The projects that actually call an LLM API in their core logic turn out to be two sub-100-star projects: AutoRestTest and api-automation-agent. This article pins down why: structured API input/output is naturally suited to traditional fuzzing, so what can LLMs actually do here that traditional tools can't β and why does this domain stay cautious instead of going all-in the way UI automation has?
Β·13 min
LLMAutomated TestingSelf-Healing
LLM-Driven Automated Testing Series (10): Self-Healing Locators β Where Heuristic Scoring Hits the Ceiling of Semantic Understanding
Healenium is the most established open-source project in self-healing locators, and its README claims it 'leverages machine learning' β but reading the code directly reveals the core mechanism is a weighted scoring formula over DOM tree similarity, with hardcoded constants for weights and thresholds, nothing to do with machine learning. More notably, its 2026 addition of an AI-based XPath generation endpoint is gated behind a hard-coded exception: 'you must have a paid hlm-ai service.' This article first cracks open exactly how Healenium's scoring formula works, then examines how MarketSquare/robotframework-selfhealing-agents β a genuinely LLM-based self-healing project β designs its multi-agent architecture, and finally answers the question the planning doc raised: where exactly does the tradeoff between healing success rate and false-positive rate actually bite.
Β·14 min
LLMAutomated TestingMetaGPT
LLM-Driven Automated Testing Series (09): Mobile Automation (V) β When a Generic Agent Framework Sinks Down into a Testing Scenario
MetaGPT is a 'multi-agent software company' framework built for requirements analysis and code generation, but it ships a built-in Android testing demo. Reading the source directly overturns one premise from the planning doc: this demo does not reuse MetaGPT's usual Product Manager/Engineer/QA role division β it has exactly one custom Role, reusing instead the lower-level Team/Environment/Role/Action scheduling scaffolding. More importantly, the README states plainly that it 'referenced ideas and code from AppAgent' β this piece breaks down exactly what this generic framework inherited from AppAgent, what reusing generic scaffolding actually bought it, and what it cost.
Β·15 min
PRODUCTS
Things I've Built
Independent products, from idea to launch β all by myself
NEW
Live
PrimeSkills
AI skill marketplace β build your personal AI avatar and enterprise digital employees
MapStory
Tell your travel stories with maps, record every journey
Plan A
Goal-driven task management that turns plans into action
π€
Jarvis AI
Your personal AI assistant that knows you better every day
π
EasyNotes
AI-powered smart notes for effortless knowledge management
π
6Sigma Tools
R&D quality management tools for continuous process improvement
PODCAST
Let's Talk
Sharing tech insights and life thoughts on podcasts
βοΈ
Subscribe to Newsletter
Curated content delivered to your inbox weekly β tech insights, product updates, and industry trends. No spam, unsubscribe anytime.
We only collect your email for the newsletter and will never share it with third parties. Unsubscribe anytime.
1,024 subscribers Β· Privacy-first, never shared
Find Me
Follow me on these platforms for the latest updates