thomasfromcdnjs

A lot of people use our gist hosting option.

You create a gist called resume.json and it automatically get's render by the registry e.g. https://registry.jsonresume.org/thomasdavis

Convenient because it is versioned, editable and hosted (forever-ish) by Github.

chatgpt can easily do that? What was the last time you tried?

There are some passionate naysayers in here.

I love "Translate this page" in Chrome, better than nothing.

Legend, thank you!

Aha fo sure.

I'm thinking of writing an MCP server that does this, just takes my night of vibe coding and recent commits/branch etc

Then just cobbles it into an AI post and adds it my blog under some category.

"Written by a human [0]"

I've been playing around with this on my own blog.

I'd like the blogging community to have a consensus on a nice badge we can put at the top of our blog posts, representing who/what wrote the post;

- human

- hybrid

- ai

Some might hate the idea of a fully "ai" post, and that's fair. But I like to sometimes treat my blog as just a personal reference, and if after a long day of chasing an esoteric bug down, I don't mind an AI just writing the whole post and I just press publish.

This adds, a reference for me, more data for AI's to train on, more pages for people to search and land on.

I love scrabble, it may be going through a growth spurt at the moment, kind of like chess after all the netflix movies.

Everyone should follow Will Anderson, he runs an extremely high quality Youtube channel -> https://www.youtube.com/@wanderer15

Even if you don't play often, his scrabble videos are fantastic to watch on a lunch break.

---

My friends and I are playing around with vibe coding a 4+ multi player scrabble, surprisingly it doesn't really exist. (hasbro is extremely tight on their copyright)

Does mid six figure mean ~$500k?

That sounds insane for a crud app with one million users.

What am I missing?

I'd guess the prompts and employees.

I've found Windsurf more reliable/efficient than any other editors by leagues. How ever they have named the tools, crafted their prompts and generally how their internals reason is just on the money. I don't think that is easy to replicate, iterating on prompts over product releases whilst not pissing off your user base constantly is a feat in of itself.

Oh great thinking.

I will have a play around, I might be able to import your package into the registry, and then anyone can serve it via http://registry.jsonresume.org/thomasdavis.mcp or something like that

This is cool, going to steal some ideas.

I started working on this mcp server that updates your resume based off what you have been doing in your editor/git-commits -> https://www.npmjs.com/package/@jsonresume/jsonresume-mcp?act...

e.g. if you were coding a supabase feature, it checks your resume for supabase and adds it if its missing.

I just sorted my drive by last modified ascending, I started using Google Docs in 2008, I don't remember using anything other than that since.

I did not realize how many people on HN are still using MS suite, a nice refreshing bubble buster.

Curious thought, thanks for sharing.

And to think that he thinks that is even more folly.

Thanks for the answer.

And http caching is definitely a huge factor for me too, graphql gives me similar sorts of pain. Sure, you can cache anything if you hack around for long enough, but in a real world engineering org (not the unicorns or uniquely positioned tech giants), it's so much easier for me to tell the CEO I can put some cache headers in by end of day and move on.

Portions of the react community are excited about how it's starting to feel more like PHP with the movement towards server actions in "client" code etc

I personally don't like that direction so looking forward to exploring new frameworks.

What I've generally liked about React/Next setups is that the code is generally explicit and less magic (I also have gripes with hooks feeling like magic). Things like Vue/Svelte where they mash together css and js in the same file if you want kind of turns me off.

Does anyone know if SolidJs projects are fully js?

This was the image: https://imgur.com/a/cCUvgDG

I uploaded this image that I screenshotted off Google street view (no metadata) and it got with 200m.

https://chatgpt.com/share/6801bbf7-fd40-8008-985d-75c8813f55...

There is the chat.

Weirdly it said, "I’ve seen that exact house before on Google Street View when exploring Cairns neighborhoods."

I am building this with a team currently and we are launching in a couple days.

Would love an alpha tester or two if anyone wants to test it.

My email/twitter is in my profile, shoot me a message and I will be in touch.

lmao I did similar.

Baha

Awesome.

Can you do a write up on that beautiful rendering? my lord.

This is awesome, well done!

Love it

Someone should parse HN api and figure out total dash usage and see if there is a spike in recent times aha

I write poems a fair bit and use em dash a lot. (maybe too much and incorrectly)

Do you run the mcp servers in the cloud, or just download them to be installed in vscode?

aha can't disagree with that sentiment, best I can do is not make the standard suck.

I've been working on BLAH - Barely Logical Agent Host (https://github.com/thomasdavis/blah/blob/master/packages/cli...) for the past few weeks.

It is essentially a standard (has a schema) that has an ecosystem of tools around it.

(completely opensource, no protocol/bridge lockin, no vendor/provider lockin, no ide/client/auton lockin, http/sse/jsonrpc/whatever, local/remote, composable)

So far I'm categorically calling MCP a "bridge", because BLAH supports other bridges such as SLOP (https://github.com/agnt-gg/slop/blob/main/README.md) and conceptually OpenAPI (or simply HTTP) is a bridge.

An example blah.json looks like this

   "tools": [
       {
         "name": "jsonresume",
         "bridge": "mcp",
         "command": "npx -y @jsonresume/mcp@3.0.0",
       },
       {
         "name": "slop_example",
         "description": "Slop example",
         "bridge": "slop",
         "source": "https://ajax-valjs_slop_example.web.val.run"
       },
       {
         "name": "normal_http_example",
         "description": "Normal HTTP example",
         "bridge": "openapi",
         "source": "https:/example.com/openapi.json"
       }
     ],
   }

So blah can orchestra/compose any number of bridges, and it can list any tools it style/format of any bridge. (sorry that sounds so dumb)

For example, you can run `blah mcp start --config blah.json`, and add that to your cursor/claude mcp servers. When you fetch the tools, it loops over all your tools in your blah.json and fetches them whether it is an mcp server, slop server or openapi, it's agnostic and will return a full list of tools pulling from all bridges.

And then you can do `blah slop start`, which will do the same, but the opposite, start a slop server but it will boot up mcp servers and serve them over http too.

So essentially a bridge/protocol agnostic system, you ask for a list of tools, and it traverses everything that can list tools and splats them all together.

That's a little of the main pitch but there are larger plans to try build an ecosystem like npmjs where there is a public registry of any tool (which are just functions at the end of the day). Clouldflare AI team is really getting it right now (https://blog.cloudflare.com/remote-model-context-protocol-se...), most people would rather just tools being hosted for them, and workers is perfect for that.

It also means you just have to add one MCP server and use one configuration file to manage your tools. (Also has way more control over logging which MCP devs would love)

---

And that all maybe sounds complicated, but it's meant to make things A LOT easier. The README.md is horrible, just lots of random ideas and my comment isn't much better, but I'm aiming to have an alpha version in a week or so. Would absolutely love feedback!

4.5 Deep Research Report on BLAH - https://gist.github.com/thomasdavis/3827a1647533e488c107e64a...

Does anyone know the correlation between our abilities to parse PDF's and the quality of our LLM's training datasets?

If a lot of scientific papers have been pdf's and hitherto had bad conversions to text/tokens, can we expect to see major gains in our training and therefore better outputs?

You probably generated a lot of back links. I would just add some more content to the page that establishes you as the original, how the game works etc

Fix up the page content for SEO and you should always appear first anyway.