Ben Hong 🦋

I got tired of looking up the syntax for checking what processes are running on the 3000 port, so I created an alias for it:

📍 I made a new drawing about Context Windows. About “lost in the middle”, how RAG affects it, tokenizers and more. Understanding context windows help you debug and leverage LLMs most effectively. You see why people like Boris from Claude refresh the entire window at times.

Never underestimate how much time and effort you can waste by trying to automate a process you do not understand manually.

This paper about throttling web agents using Reasoning Gates is pretty interesting! For stealth agents that ignore no-crawl directives, they give them multi hop tests of intelligence- It gives the agent very complex logic problems to solve that it would take humans hours of research to do. For an agent, it takes a matter of seconds. The token usage is low for answering once, but too high for multiple attempts. So it introduces computational asymmetry. Getting to an airline site- negligible. But deploying many many agents to perform malicious scraping/DDoS? The server bills alone would bankrupt malicious actors before they got anywhere. arxiv.org/html/2509.0161…

It's funny to me that the hype train around AI wants the narrative of "you don't need to code anymore" to be a reality. As if anyone who enjoys coding is insane to do so since "AI can do it."

There's definitely something magical about attending these events in-person that doesn't even remotely get captured in virtual events. I have so many good memories of all the past @vueconfus and looking forward to creating many more this year. Hope to see y'all there!

I gave a talk last week and someone asked why we need an agent model for the web- The web needs an established interface layer. WebMCP, though not complete, is part of a strong foundation- it exposes structured endpoints agents can use directly, giving a clearer defined course. I, for one, don’t want agents YOLO’ing around like the wild west. We can build structured well lit paths for better security, rate-limiting, and give observability and control to users.

Always look at incentive structures. On here, this means inflammatory and overly simple statements gain traction- "open source is dead!" or "Software Engineering is dead!" etc A nuanced post exploring tradeoffs and considerations will be drowned out for a hypey quip for debate

Excited to give my first AI talk at @RefreshDC! eventbrite.com/e/tdd-add-ddd-…

if your data is stored in a database that a company can freely read and access (i.e. not end-to-end encrypted), the company will eventually update their ToS so they can use your data for AI training — the incentives are too strong to resist

Level up your Vue apps! 🚀 In this hands-on workshop, @bencodezen shows how to build production-grade @Vuejs apps using reusable patterns, automated workflows, and testing best practices for real-world projects. vueconf.us/session?sessio… 🎟️ Get tickets- vueconf.us

I can't go back to the regular YouTube UI after this 😅 Obsidian Reader now makes the transcript interactive so you can scrub, highlight, auto-scroll. It feels so nice.

It's taken a couple of years, but it's time... Time to revamp my website from the ground up.

Workshops at VueConf US = next-level learning for @vuejs devs 🚀 Roll up your sleeves. Ask questions. Build alongside the experts. 🔗 Details: #workshops" target="_blank" rel="nofollow noopener">vueconf.us/#workshops With David Nahodyl, @danielkelly_io, @bencodezen, @martinrojas & @joemocha 🎟️ vueconf.us

‼️Do not npm install or deploy anything right now Supply chain attack on axios 1.14.1 - even if you don’t use axios it may be a nested dep. Pin versions or wait until this is resolved

Realizing that vibe-coders who don't read the code are gonna have a bad time Debugging AI-generated code is 10x faster when you can say "I think the bug is here" vs. just pasting an error and praying

If you use GitHub (especially if you pay for it!!) consider doing this *immediately* Settings -> Privacy -> Disallow GitHub to train their models on your code. GitHub opted *everyone* into training. No matter if you pay for the service (like I do). WTH github.com/settings/copil…

Vibe coding an app and shipping it feels a lot like opening a cafe where the food tastes pretty good, but you have no idea whether it's going to give your customers food poisoning later on.

March MadCSS Round 1 PART TWO (the right side of the bracket) starts in ONE HOUR at 10AM on YouTube. @KevinJPowell vs @selfteachme @JoshWComeau vs @cassidoo @wesbos vs @bencodezen @ania_kubow vs @argyleink

Tomorrow at 10AM EST!! who you got your money on? @KevinJPowell vs @selfteachme @JoshWComeau vs @cassidoo @wesbos vs @bencodezen @ania_kubow vs @argyleink

There’s a massive difference between using AI to solve a problem vs using it to generate a solution. The output looks the same, but the growth is worlds apart. Sadly, it seems most people are settling for the shortcut and missing the true value of AI.