joshuanapoli

Joined 16 years ago

Karma

519

Submissions

264

Member since

May 12

View on Hacker News

Recent submissions

Comment · 7 days ago

I disabled tab completion. When I open a file in an IDE, it is because I don’t want an AI edit; I’m fixing the confusing documentation, or changing a configuration, or making a small edit to the code. I do code changes through the agent, because it is more accurate and thorough.

I don’t think that I would use tab completions again. I bet that there will be some innovation in how code is visualized, though.

Comment · 23 days ago

If you have a custom agent in a product, then it needs isolation to be sure to protect the customer data.

Comment · 1 month ago

CVector builds software to bring real time economic optimization and AI prediction to every energy and manufacturing plant. We integrate real-time data visualization and analytics to help power generation stations, chemical plants, and other critical infrastructure make informed decisions in rapidly changing environments. You'll help create intuitive, robust web apps, machine learning models and backend systems, shaping tools that directly impact industrial operations and energy reliability. Build AI agent systems that automatically foresee upcoming problems and provide possible solutions.

Full Stack and Backend Software Engineers: We're looking for a passionate Software Engineers comfortable working across our stack (Python, Typescript, React, Supabase, MQTT, TimescaleDB, PostgreSQL, AWS, FastAPI) or someone to specialize in our backend infrastructure.

Senior Research Engineer: Candidates should be experienced with machine learning, and analysis using Python.

Reach out to me at [email protected]

Comment · 1 month ago

We have some company-managed skills, that help coding agents find the relationships between our repos, and our conventions, architecture, and other high-level decisions. These are supposed to be portable between agents, and so distributing them is currently awkward.

We have a bootstrap script to deploy company-managed skills to each developer's "personal" skills. Hooks for codex and claude code try to refresh the skills on each startup.

Comment · 3 months ago

I don’t think that anyone would want to steal an icebreaker, but a datacenter full of valuable equipment and interesting information is a more likely target.

Comment · 5 months ago

I've been thinking of reverting back to Circle CI.

Comment · 5 months ago

Does zizmor catch this pull_request_target vs cache poison vulnerability?

Comment · 5 months ago

Rewrite following a new architecture plan could get finished pretty quickly, treating the original as a prototype.

Comment · 7 months ago

CVector recently raised $5M seed, read more on TechCrunch: https://techcrunch.com/2026/01/26/ai-startup-cvector-raises-...

Senior Research Engineer: Candidates should be experienced with machine learning, and analysis using Python.

Reach out to me at [email protected]

Comment · 7 months ago

They use a bespoke language to define LLM-generated UI components. I think that this is supposed to prevent exfiltration if the LLM is prompt-injected. In any case, the parser compiles chunks streaming from the LLM to build a live UI. The WASM parser restarted from the beginning upon each chunk received. Fixing this algorithm to work more incrementally (while porting from Rust to TypeScript) improved performance a lot.

Comment · 8 months ago

CVector builds software to bring real-time economic optimization and AI prediction to every energy and manufacturing plant. We fuse live asset data with market dynamics into one decision layer that continuously forecasts, simulates, and optimizes — so plants run closer to their true economic potential every day. CVector recently raised $5M seed, read more on TechCrunch: https://techcrunch.com/2026/01/26/ai-startup-cvector-raises-...

We're looking for a senior backend engineer to evolve our core platform — time-series data systems, AI-assisted analytics, cloud infrastructure, and data ingestion pipelines. You'll take ownership of complex systems, drive major technical migrations, and shape how intelligence is embedded into industrial energy workflows. Think: AI evals and prompt engineering, MQTT ingestion pipelines, time-series schema design, PostgreSQL infrastructure, and ML platform support.

Stack: Python, TypeScript, Supabase, PostgreSQL, MQTT, TigerData, InfluxDB, AWS. 5+ years experience building production backend systems. FinTech, quantitative analysis, or econometrics background is a strong plus.

$125K–$150K + meaningful equity. Reach out to me at [email protected]

Comment · 8 months ago

WebMCP should be a really easy way to add some handy automation functionality to your website. This is probably most useful for internal applications.

Comment · 9 months ago

CVector recently raised $5M seed, read more on TechCrunch: https://techcrunch.com/2026/01/26/ai-startup-cvector-raises-...

Senior Research Engineer: Candidates should be experienced with machine learning, and analysis using Python.

Reach out to me at [email protected]

Comment · 9 months ago

This looks nice! I like the idea of providing more deterministic feedback and more or less forcing the assistant to follow a particular development process. Do you have evidence that gtg improves the overall workflow? I think that there is a trade-off between risk of getting stuck (iteration without reaching gtg-green) versus reaching perfect 100% completion.

Comment · 10 months ago

Merry Christmas from Rhode Island!