Hacker Newsnew | past | comments | ask | show | jobs | submit | thomasfromcdnjs's commentslogin

+1 and also add a feature for unique words to show how you vocab ranks

> unique words to show how you vocab ranks

I think writing well with plain language would be a better indicator of worthwhile contributions than estoeric jargon that only serves to confuse or intimate. That would be a lot more difficult to measure though, the number of fancy words per post probably is a lot easier to vibe code.


Yes I agree with this 100%

One of the things in future I wish to personally learn is how to write concisely. My posts are large and scattered.

To me, the beauty was in the depth/content in Hackernews. I still remember the day when HN clicked to me when I was in metro. A comment clicked with me and really changed my perspective on something. It was fairly long from what I can tell (I am sorry but I am a little hazy other than I was going/returning to school and I was using hackernews)

HN comments are great the way they are. Let's keep it that way.

> That would be a lot more difficult to measure though, the number of fancy words per post probably is a lot easier to vibe code.

Agreed, I use it for prototyping but I am still learning. I hope to not vibe code as I progress and go to college for example. Currently I was constrained because I was (sad?) from my last exam not going so well & the next one being in 8 days ish.

Wish me luck :)

The only reason I vibe code is either for prototyping (for time constraints) and I just wanted to share it to the world.

I have actually written a lot about it. I hope you can read it if you have time [all comments are and will always be written by me] :)

Have a nice day! I am just happy that it can be on front page :]


intimidate

;)


Yes, that is a typo!

You get double points for that one

Please don't start subtracting for em-dashes though. ;-)

It will be skewed due to all the jargon, slang and grammar errors.

But if it is equally skewed for everyone, does it really matter?

It probably doesn't have a large enough effect to matter, but I would expect that it would negatively impact the people you're trying to positively impact by using this metric. If you're careful with your words, a better typist, refrain from slang, reread your posts multiple times, edit out typos or inconsistencies or rambling thoughts, this type of vocabulary ranking would "hurt" you. But if you do that you're also probably the type of person to write longer more well thought out comments. So it's probably a wash to slightly "achieving the opposite of what you want but not really enough that you'd notice it" if I had to guess.

I keep trying to use Codex CLI but I love using claude --dangerously-skip-permissions but this seems impossible to do in codex, and it just asks me to approve every command per session. Am I taking crazy pills or is there a way to make codex just run in yolo mode?

--yolo

could find in --help


I'm working on tpmjs.com the npm registry for ai tools (just the vercel ai sdk flavor atm)

which lets users create collections of any publicly available tool which let's us do awesome things

We can auto generate a skills.md for collections https://tpmjs.com/ajax/collections/unsandbox/skills.md (https://tpmjs.com/ajax/collections/unsandbox to see the collection)

We analyze all the tools source code to write the skills.md using LLM's and then we auto inject three different ways agents can iteract with them

- hosted mcp servers for collections automatically e.g. https://tpmjs.com/api/mcp/ajax/unsandbox/sse

- a cli tool that can invoke each tool in the collection e.g. tpm run --collection ajax/unsandbox --tool [tool-name] --args '{"key": "value"}'

- restful endpoints for direct execution of tools e.g. curl -X POST https://tpmjs.com/api/mcp/ajax/unsandbox/http

It's very much alpha, but after building this, I don't see why you can't let agents choose any method they want of interacting with your service.

It means your agents can use CLI, MCP or REST, only in one style or any style all at once.


Please make a rest API!


Agreed. I've worked in startups most of my career, I've messaged CEO's, CEO's have been messaged, never a negative experience and higher quality candidates in my opinion.

Side note: You gotta hustle people!


I've been slowly working on https://blocksai.dev/ which is a framework for building feedback loops for agentic coding purposes. It just exposes a CLI that can run custom validators against anything with a spec in the middle. It's goal being like the blog post is to make sure their is always a feedback loop for the agent, be it programmatic test, semantic linting, visual outputs, anything!


Why not just give him a branch? I've found underestimating "non-technical" people a folly in the AI era. They can easily boot up projects with agentic AI assistance.


I created a "mcp server" for sprites yesterday through this new ecosystem I am working on, you can clone the collection, and then just add this https://tpmjs.com/api/mcp/ajax/sprites/sse mcp sse url to claude desktop, or anything you want.

tpmjs is a registry of ai sdk npm packages (i created them for sprites), which you can add to personal collections, we automatically server your collections as mcp servers if you want.

Creating sprites in an example chat bot -> https://imgur.com/a/ETNxR1o

Creating sprites in claude desktop -> https://imgur.com/myC0U28

Listing out my sprites in claude desktop -> https://imgur.com/rgBU0jm

---

You can view the collection of tools here -> https://tpmjs.com/ajax/collections/sprites (fork it to use it yourself)

I'm looking into exe.dev and sprites.dev to build out extra features into tpmjs, agent sandboxes make a lot of sense.


Kind of crazy your original post got flagged, it was completely reasonable.

---

> which ironically I think Scott would have liked

Agreed, RIP.


I'm working on an overly ambitious project called tpmjs.com, making good progress, it's meant to do "everything" in relation to mcp, agents and tools etc

I like your thought process, and agree with it all.

Everything other than what you described towards the end seems easy to build useful abstracts around.

I'm going to tackle the problem this weekend, probably just use Lightroom mcp as the example, I don't have any good ideas to begin with;

- These applications should probably adapt their codebase to the evolving landscape (that might take a while so in the interim...)

- Another easy idea, is to boot up a sandbox and runs the software, maybe even shares projects across mcp users or something, a service orientated model but pretty much sucks too

- Best but kind of worst idea I have so far is to just make a software service that users download and run that orchestrates software and processes etc (kind of like anti cheating software or something, with far too elevated permissions)

A bit stressed for time so couldn't distill what I think properly just yet, will edit later)


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: