writing
Blog
Field notes from the TRAGenX desk — AI trading, fintech, security, and the craft of vibecoding.
Gemini Comes to Apple CarPlay: Conversational Navigation in the Car
Google is bringing conversational Gemini navigation to Apple CarPlay, almost a year after it reached Android Auto. For builders, the car is now a test of voice-first AI under strict safety limits.
- gemini
- carplay
- voice-ai
- agentic-ux
- google-maps
Battle Drones: A Vibe-Coded RTS and the Agent Loop That Made It Fun
Simon Willison's Battle Drones went through 12 major iterations and 321 commits, mostly written by coding agents. The most useful parts for builders are how the agent tested its own game and why a deterministic simulation was needed.
- vibecoding
- agentic-dev
- claude-code
- game-dev
- testing
Gemini's Personal Intelligence Reaches the Car: What Agents With Your Data Mean
Google says Gemini in Android Auto and cars with Google built-in can now draw on your Gmail, Calendar, Maps, Photos, YouTube and Search. The cabin is becoming a test of how personal-context AI should be scoped.
- gemini
- android-auto
- ai-agents
- personal-context
- guardrails
The 'Obituary for Programming' and What Coding Agents Take Away
Jeremy Scheff's essay, amplified by Simon Willison, names a loss that benchmarks don't measure: the puzzle-solving craft that made programming a good job. For builders shipping with agents, it points at where human judgment still has to live.
- vibecoding
- coding-agents
- software-engineering
- ai-assisted-development
Philly Arrest Over a Blocked Delivery Robot Shows the Human Side of Autonomy
A Philadelphia woman was charged with disorderly conduct after blocking an Uber delivery robot to protest job losses. The case shows that autonomous systems share the sidewalk with people, and some of those people will push back.
- delivery-robots
- autonomy
- ai-safety
- edge-cases
- agents
LLM 0.33's httpx2 switch broke plugins that never declared httpx
Simon Willison's llm-tools-datasette 0.1.1 fixes a plugin broken by LLM 0.33's move to httpx2. The cause is a familiar packaging trap: importing a library you never declared as a dependency.
- llm
- datasette
- python
- dependencies
- agentic-tooling
Gemini 4 Argon is GA at $2/M input, but the price is introductory
Google's Gemini 4 Argon went generally available on October 13 at $2 input and $10 output per million tokens. The rate is introductory, so agent and trading-research teams should model the post-promo price before committing.
- gemini
- llm-pricing
- agentic-workflows
- ai-engineering
- trading-research
Websites Are Closing Their Doors to AI Agents: What Builders Should Do
The Verge reports that autonomous agents promising to book, buy and tidy up on your behalf are running into sites that won't let them in. For anyone shipping agents, access is now an engineering constraint rather than a given.
- ai agents
- web access
- robots.txt
- agentic engineering
- automation
Anthropic's $16.8bn quarter: what the investor numbers mean for builders
Anthropic reportedly told investors its Q3 revenue reached $16.8bn, with $1.70 earned for every $1 spent on compute. For anyone building on frontier models, the unit economics and the distillation detail matter more than the headline.
- anthropic
- llm
- ai-economics
- distillation
- ai-tooling
RTX Spark: What Nvidia's Arm Laptop Chip Means for Local AI Dev
Nvidia's N1X-based RTX Spark has reached reviewers in laptops from multiple makers. For builders, the question is whether an Arm laptop with an Nvidia GPU becomes a real daily-driver for AI-assisted development and local model work.
- nvidia
- arm
- local-llm
- developer-tools
- hardware
Meta's Muse Spark Open Targets Two Mac Studios and MLX
Meta calls Muse Spark Open the most capable US open-weight model to date, and says it runs on a two-machine Apple desktop setup. For builders, the hardware pitch matters as much as the benchmark claim.
- open-weight
- mlx
- local-inference
- apple-silicon
- meta
Bluesky's Attie Moves From Custom Feeds to Shareable Mini Apps
Bluesky's AI tool Attie started as a way to build your own feeds. It now lets people describe small social apps, such as games, polls and dashboards, and share each one as its own website. It is another sign that vibecoding is moving from developer tooling to ordinary users.
- vibecoding
- bluesky
- ai-agents
- social-apps
- developer-tools
OpenAI Says an Ex-Employee Took 100+ Files to Apple: What Builders Should Learn
OpenAI alleges a former employee sent more than 100 product-plan files to a personal account and then presented them to Apple leadership. The allegations are unproven, but the case is a useful prompt to check how your own team's data can leave.
- openai
- apple
- insider-risk
- ai-security
- data-governance
Shopify opens its catalog to more AI agents, and shoppers set the rules
Shopify says more AI agents will soon be able to browse and buy from its listings on a shopper's behalf. For anyone building agents that transact, the interesting part is who configures them.
- agentic-commerce
- shopify
- ai-agents
- payments
- fintech
Anthropic Replaced Git with Scion: Source Control Built for AI-Agent Volume
Anthropic says its monorepo went from about 2,500 merges a day in May 2026 to over 30,000 in September, and Git stopped fitting. Its replacement, Scion, assumes clients that are always online.
- vibecoding
- source-control
- ai-agents
- git
- developer-tooling
Archive
Showing the latest 15 of 189 postsTopics
- Vibecoding104
- AI Agents40
- Openai36
- Agentic AI32
- AI Safety22
- Anthropic16
- Claude12
- AI Hardware11
- Dev Tooling11
- LLM11
- LLM Security11
- Agentic Coding9
- LLM Safety9
- Meta9
- AI Assisted Development8
- AI Coding Agents7
- AI Policy7
- AI Security7
- AI Tooling7
- Claude Code7
- Gemini7
- LLM Pricing7
- AI Infrastructure6
- Coding Agents6
- Fintech6
- Generative AI6
- Risk Management6
- Agentic Dev5
- Agentic Tooling5
- Agents5
- Chatgpt5
- Developer Tools5
- LLM Agents5
- LLM Tooling5
- MCP5
- Python5
- Software Engineering5
- SQLITE5
- Webassembly5
- Agent Safety4
- AI Models4
- Apple4
- Guardrails4
- Nvidia4
- Open Weight Models4
- Sandboxing4
- Voice AI4
- AI Tools3
- AI Trading3
- AI Writing3
- Algorithmic Trading3
- Automation3
- Codex3
- Datasette3
- Evals3
- Gpt 5.63
- Gpt 6 Astra3
- Hardware3
- Local Inference3
- Microsoft3
- Model Evaluation3
- On Device AI3
- Open Source3
- Prompt Injection3
- Regtech3
- Trade Secrets3
- Agentic Commerce2
- Agentic Finance2
- Agentic UX2
- AI Coding Tools2
- AI Copyright2
- AI Dev Tools2
- AI Regulation2
- Algo Trading2
- Apple Silicon2
- Arm2
- Aws2
- Bitcoin2
- China AI2
- Ci Cd2
- Cloudflare2
- Compliance2
- Copilot2
- Data Centers2
- Dev Tools2
- Devday2
- Developer Tooling2
- Distillation2
- Engineering Culture2
- Enterprise AI2
- Ethereum2
- Frontier AI2
- Game Dev2
- Github Copilot2
- Hedge Funds2
- Ipo2
- LLM API2
- LLM APIS2
- LLM Benchmarks2
- LLM Governance2
- LLM In The Loop2
- LLM Tools2
- LLM Workflow2
- LLMS2
- Mlx2
- Open Weight2
- Open Weights AI2
- Privacy2
- Qwen2
- RAG2
- Smart Glasses2
- Spacexai2
- Supply Chain Security2
- Training Data2
- Verification2
- Voice Interfaces2
- Zk Rollups2
- Account Abstraction1
- Accountability1
- Acquisitions1
- Agent Architecture1
- Agent Reliability1
- Agentic1
- Agentic Dev Tooling1
- Agentic Dev Tools1
- Agentic Development1
- Agentic Engineering1
- Agentic Security1
- Agentic Tools1
- Agentic Trading1
- Agentic Workflows1
- AI Assistants1
- AI Codegen1
- AI Coding1
- AI Coding Costs1
- AI Crawlers1
- AI Disclosure1
- AI Economics1
- AI Education1
- AI Engineering1
- AI Ethics1
- AI Governance1
- AI Industry1
- AI Inference1
- AI Investment1
- AI Knowledge1
- AI Litigation1
- AI Math1
- AI Misuse1
- AI Music1
- AI Provenance1
- AI Reliability1
- AI Research1
- AI Security Audit1
- AI Strategy1
- AI Transparency1
- AI Watermarking1
- Alexa1
- Alibaba1
- Altcoins1
- Amd1
- Aml1
- Andreessen Horowitz1
- Android Auto1
- Android Xr1
- Antitrust1
- API1
- API Abuse1
- Apple Intelligence1
- Appsec1
- Audio1
- Autonomy1
- Biotech1
- Blender1
- Blockchain Infrastructure1
- Bluesky1
- Browser Automation1
- Browser Engineering1
- Browser Tools1
- C2pa1
- Carplay1
- China AI Regulation1
- Claude Cowork1
- Claude Fable 51
- Claude Fable 5 11
- Claude Fable 5.11
- Claude Opus1
- Claude Opus 51
- Claude Sonnet 51
- Cloud Costs1
- Code Review1
- Coinbase1
- Compute1
- Computer Use1
- Context Window1
- Conversational AI1
- Corporate Treasury1
- Credential Security1
- Crowded Trades1
- Crypto Accounting1
- Crypto Derivatives1
- Crypto Futures1
- Crypto Infrastructure1
- Crypto Regulation1
- Cybersecurity1
- D31
- Dario Amodei1
- Data Extraction1
- Data Governance1
- Data Licensing1
- Data Privacy1
- Delivery Robots1
- Dependencies1
- Developer Experience1
- Developer Hardware1
- Devsecops1
- Devtools1
- Distributed Compute1
- Dns Abuse1
- Documentation1
- Edge AI1
- Edge Cases1
- Edge Inference1
- Eip 77021
- Embeddings1
- Energy1
- Energy Costs1
- Engineering Management1
- Engineering Process1
- Ethereum L21
- Eu AI Act1
- Eval Infrastructure1
- EVM1
- Executive Order1
- Export Controls1
- Ffmpeg Wasm1
- Fintech Engineering1
- Fintech Regtech1
- Fintech Security1
- Formal Proofs1
- Fraud1
- Funding1
- Fusaka1
- Game Development1
- Gemini Notebook1
- Generative UI1
- Geospatial1
- Git1
- Github Actions1
- Github Models1
- Google1
- Google Adk1
- Google AI1
- Google Deepmind1
- Google Gemini1
- Google Maps1
- Governance1
- Government AI1
- Gpt 61
- Greg Brockman1
- Grok1
- Grok Cli1
- Grokipedia1
- Grounding1
- Home Automation1
- Image Generation1
- Insider Risk1
- Institutional Capital1
- Iot1
- Jailbreak1
- Jeff Dean1
- Jony Ive1
- Kimi K31
- Kotlin1
- Kyc1
- Layer 21
- Leaky Abstractions1
- Legacy Systems1
- Leverage1
- Live Avatar1
- LLM Architecture1
- LLM Copyright1
- LLM Deployment1
- LLM Engineering1
- LLM Evaluation1
- LLM Inference1
- LLM Infrastructure1
- LLM Oversight1
- LLM Routing1
- LLM Trading Safety1
- LLM Transparency1
- LLM Workflows1
- Local AI1
- Local LLM1
- Local LLMS1
- Local Models1
- Macos1
- Macro Data1
- Maia1
- Market Volatility1
- Math Research1
- Mathematics1
- Matter Labs1
- Mediapipe1
- Meta AI1
- Microsoft Copilot1
- Minors1
- Mistral1
- Mixture Of Experts1
- Model Context Protocol1
- Model Pricing1
- Model Releases1
- Model Safety1
- Moonshot AI1
- Multimodal AI1
- Muse1
- Notebooklm1
- Open Source AI1
- Open Weight LLM1
- Open Weights1
- Openai Codex1
- Openai Responses API1
- Openrouter1
- OPFS1
- Packaging1
- Payments1
- Personal Context1
- Phishing1
- Power1
- Pyodide1
- Python Tooling1
- Quant Finance1
- Quant Funds1
- Reasoning1
- Regex1
- Regulation1
- Reverse Engineering1
- Robinhood1
- Robots.txt1
- Rubygems1
- Serverless1
- Shopify1
- Simon Willison1
- Siri1
- Smart Contracts1
- Smart Home1
- Social Apps1
- Solidity1
- Source Control1
- Spacex1
- Startup Talent1
- Suno1
- Superintelligence1
- Surface1
- Svg1
- System Prompts1
- Tech Debt1
- Tech Law1
- Tech Litigation1
- Technical Debt1
- Temasek1
- Testing1
- Text To Speech1
- Thinking Machines Lab1
- Trading Agents1
- Trading Automation1
- Trading Research1
- Typesafe AI1
- Us Politics1
- Uv1
- Vendor Risk1
- Voice Agents1
- Wearable AI1
- Wearables1
- Web Access1
- Web Scraping1
- Web3 Infrastructure1
- Windows1
- World Models1
- X4021
- Y Combinator1
- Zero Trust1
- Zkevm1
- Zksync1