HackerTrans
TopNewTrendsCommentsPastAskShowJobs

Norcim133

no profile record

Submissions

[untitled]

1 points·by Norcim133·há 4 meses·0 comments

Ask HN: How does Boardy achieve such low latency?

1 points·by Norcim133·há 7 meses·1 comments

The best intro video to blockchain is from 2013

youtube.com
3 points·by Norcim133·há 8 meses·0 comments

Show HN: Our First Demo Video for an AI Ass

youtube.com
1 points·by Norcim133·há 8 meses·1 comments

Ask HN: What's the best tool for startup explainer videos?

2 points·by Norcim133·há 9 meses·0 comments

Our Voice-AI Assistant Hit Unit Profit – Thanks to Haiku 4.5

indiehackers.com
1 points·by Norcim133·há 9 meses·0 comments

High-end AI model, freemium offering, founder bootstrapping – Choose 2

indiehackers.com
1 points·by Norcim133·há 9 meses·0 comments

My Path to Launching Palpable AI: An AI Pal That Gets. Things. Done

indiehackers.com
1 points·by Norcim133·há 9 meses·0 comments

Ask HN: Use Sentry/AppInsights vs. middleware for early stage?

2 points·by Norcim133·há 10 meses·1 comments

MCP's auth spec is lacking and Auth0 isn't helping

github.com
3 points·by Norcim133·há 11 meses·3 comments

Ask HN: What is the web template everyone uses for startups?

5 points·by Norcim133·há 12 meses·4 comments

Old paradigm spoiling new – MCP's Structured Output undermines the point of MCP

github.com
2 points·by Norcim133·há 12 meses·1 comments

Building low-feature apps is good source of calm

indiehackers.com
4 points·by Norcim133·há 12 meses·0 comments

Show HN: Zero-back-end process mining tool running Python in WASM

enthoosa.com
1 points·by Norcim133·há 12 meses·2 comments

Interactive RAG Tools Infographic

claude.ai
3 points·by Norcim133·há 12 meses·0 comments

Show HN: Outlook MCP – I accidentally made the best email assistant

github.com
2 points·by Norcim133·há 12 meses·1 comments

Deliver Your B2B SaaS App via WASM to Fast-Track Enterprise Sales

indiehackers.com
2 points·by Norcim133·ano passado·0 comments

comments

Norcim133
·há 8 meses·discuss
FWIW HN truncated the ellipses at the end of my title.
Norcim133
·há 9 meses·discuss
Anyone know how this will compare to Mem0 or Zep?
Norcim133
·há 11 meses·discuss
Seems like it isn't all the protocol? A lot of it is the and the current tools. If you have a hardcore dev who knows auth they can implement to spec and be safe/simple-ish.
Norcim133
·há 12 meses·discuss
MCP Client builders have been asking SDK builders to enforce Structured Output schemas on MCP Servers. The Python SDK has agreed.

Here I assert this is another example of an old paradigm misunderstanding a new one.

Specifically, it is traditional builders and "agentic workflow" builders misunderstanding the various roles in an MCP flow.

Namely, an MCP Client's role is to thinly connect an LLM, a user, and an API... and then get out of the way.

The LLM doesn't gain from wrapping tool output in additional metadata and boilerplate. That just makes the output harder to parse while also making it less similar to the patterns the LLM trained on.

The Client doesn't need the structure to help it orchestrate/route tools... it is the LLM's job to orchestrate.

If you want the Client to orchestrate, that's totally fine. Build with Langchain, not MCP.

The reason agentic workflows need strict adherence to structured input/output is because they are so rigid. Each interaction between one step and another is highly coupled and basically "one-shot".

To get "flexibility" across tasks, you have to layer many of these "one-shot" and coupled flows on top of each other. This is what makes agentic workflows like RPA.

Implicitly, we often treat LLMs as one-shot too. If we ask it to do a coding task, it might make up a method name and we say it hallucinated. But that's raising the bar far above what a human would face. A human would get to goole the method or see in the IDE the warning that the method doesn't exist. Our experience with flaky LLM coding is actually caused by this "one shot" assumption.

MCP flows are the opposite of one-shot. The LLM can use a tool, make a mistake with the data structure, read the error, fix it and move on. There is much lower gain to optimizing to avoid that specific mistake because the LLM still got to the right answer and, with infinite Servers/Tools, the LLM may never do that exact same flow again.

MCP affords a much more self-correcting and flexible system. To the extent there is an art to improving the LLM-Tool interaction, it lies in having the Server builder be thoughtful about how to name the tools and parameters and docstrings.

Enforcing schemas from the client actually makes the least important player (the Client) slightly better off by hamstringing the stars of the show (the LLM and the tool). The real answer, build your clients differently.
Norcim133
·há 12 meses·discuss
You nailed it. I've been serving banks who have this exact problem. They have to be so careful with their data they can only buy over-engineered solutions that barely meet their actual need.
Norcim133
·há 12 meses·discuss
Nice little site. What did you build it with?

I once leaked an API key and instantly got a mail from GitGuardian informing me of the leak. It was a) super helpful as I wouldn't have known otherwise b) it seemed like a clever way to spread their name/biz

(in case that's helpful to your model)
Norcim133
·há 12 meses·discuss
It is a fair point.

But I found this article landed different than most self-help. It spoke in terms of mindsets one can adopt to do the things you mentioned.

And it made those mindsets compact/memorable so I'm more likely to use them.
Norcim133
·há 12 meses·discuss
I'm getting an endless "Preparing Space" loop for the "See it Action" section... does that still TBD or should it work?
Norcim133
·há 12 meses·discuss
Def true when I'm using Gemini with 400k tokens in context... I toggle to Youtube while I wait and have usually started working for a new company by the time I remember to go back to what I was prompting.
Norcim133
·há 12 meses·discuss
Cool approach.

I suspect one additional unstated rule: be opinionated on tech stack.

I've noticed LLMs struggle with the seams, whenever you're using a rare stack combo.

No problem - React front + Node.js back

Runaway death spiral - Streamlit Front + iFrame React Component + Python back + running in WASM via Pyodide
Norcim133
·há 12 meses·discuss
Better than Outlook?
Norcim133
·há 12 meses·discuss
AI is an accelerator if you know one language and you're trying to go full-stack, say. The learning you get is incredible. All other use-cases are dubious. If you're a senior dev, you're still faster (once you include the debugging). If you're a junior dev it's too buggy and gets out of control as complexity increases.
Norcim133
·há 12 meses·discuss
Correct-ish. LlamaCloud and GroundX do everything up to retrieval. Here is an interactive graphic of major players along RAG flow: https://claude.ai/public/artifacts/b872435b-1d9c-461e-a29c-b...
Norcim133
·há 12 meses·discuss
It was definitely that thing with any actors/actresses. To be "good looking enough" for the screen means they are a different species IRL.
Norcim133
·há 12 meses·discuss
I spent the last 2 months trying out RAG/parsing plays. My use-case required high accuracy on complex tables and figures.

Ranking: 1. LlamaCloud/LlamaParse 2. GroundX 3. Unstructured.io 4. Google RAG Engine 5. Docling ... capability gap... 6. Azure - Document Intelligence 7. AWS - Textract 8. LlamaIndex (DIY)
Norcim133
·há 12 meses·discuss
This title speaks truth
Norcim133
·há 12 meses·discuss
They were the height of cool then.

I once found myself sitting behind Alicia Silverstone at a show. My uncle kept laughing so loudly it made Alicia turn around and glare every 10 minutes.

As a young, crushing teen it was very cringe.
Norcim133
·há 12 meses·discuss
This post is also just an elaborate ploy to test out this person's "Time Since MCP Mentioned" tracker: https://news.ycombinator.com/item?id=44638599
Norcim133
·há 12 meses·discuss
I built my own MCP server for Outlook precisely because I didn't understand all the hype: https://github.com/Norcim133/OutlookMCPServer

With a few days coding, it was a better email assistant than any person or software I've worked with over the last decade.

I've added it to Claude Desktop and use it alongside MCPs for Notion (for DB), OpenMemory (knowledge layer), fetch (web scraping), and Xero (accounting software).
Norcim133
·há 12 meses·discuss
The site was solid and the images, when you look closely, are great. Polling my emotions I found the premise enticing but also felt a knee-jerk skepticism. It's because viral is such a high bar given most clip generation plays still struggle with the much lower bar of "quality".

Therefore, if you can provide viral content, make that your "social proof" area... a "testable credentials" area... like a "today's creations" section that shows legit viral creations each week that can't have been pre-curated.