Hacker News: spennant

New comment by spennant in "You said no MCP"

spennant — Wed, 30 Sep 2026 13:26:44 +0000

The idea of "model controlled", "application controlled" and "user controlled" for tool, resources and prompts (respectively) was aligned with the chat interface. It breaks for the autonomous agent paradigm where the agency is the user and the lines are blurred. Unfortunately MCP has been mostly relegated to tool calling leaving potentially powerful capabilities on the table due to lac of client support for them.

New comment by spennant in "When did Google get so weird?"

spennant — Mon, 28 Sep 2026 02:50:59 +0000

"In a shocking finding, scientist discovered a herd of unicorns living in a remote, previously unexplored valley, in the Andes Mountains. Even more surprising to the researchers was the fact that the unicorns spoke perfect English."

New comment by spennant in "Show HN: Rickub – The Smartest Git in the Universe"

spennant — Fri, 18 Sep 2026 16:20:32 +0000

Luggage Packing Optimizer? The nerdiness level is awesome and I'm here for all of it!

New comment by spennant in "Fuck it, make it anyway"

spennant — Sat, 12 Sep 2026 14:50:55 +0000

This is my experience as well. It gets worse when the LLMs have strong priors in subject matter adjacent to your novel work. The generated output will incorrectly pull towards things the LLM has seen in it’s training data.

New comment by spennant in "Ask HN: What Are You Working On? (July 2026)"

spennant — Mon, 13 Jul 2026 00:23:50 +0000

I'm working on leveraging NLP and LLM techniques to create a geometry over the discrete space of Ethereum transaction execution structure. (sorry... it's a bit of a mouthful)

https://www.chaingenius.ai

The goal is to find on-chain structural anomalies, as well as seeing if clustering by behavior has emergent semantic properties

Show HN: Explore Ethereum by the Shape of a Transaction

spennant — Wed, 01 Jul 2026 00:25:02 +0000

I built a block explorer that allows visitors to browse the Ethereum blockchain by the shape of each transaction’s calls tree and address interaction graph. The call tree visualization is clickable ui which reveals sub-transaction as well as every other transaction that contains them. Currently the corpus only has about 1 Billion transactions (Blocks: 20800000 – 25399999) but I plan to automate the recent block ingestion as well as backfill data to The Merge. (Keeping up with the chain speed is not a current goal)

Comments URL: https://news.ycombinator.com/item?id=48740991

Points: 3

# Comments: 0

New comment by spennant in "BadHost – CVE-2026-48710: Starlette Host-Header Auth Bypass"

spennant — Wed, 27 May 2026 12:20:56 +0000

Is this still true?

New comment by spennant in "Ask HN: What are you working on? (February 2026)"

spennant — Mon, 09 Feb 2026 15:48:47 +0000

Fine tuning Gemini 2.5 flash on EVM Blockchain execution structures and using perplexity with PageRank to perform transaction anomaly detection. https://lite.chaingenius.ai/theory

[SMILES](https://en.wikipedia.org/wiki/Simplified_Molecular_Input_Lin...) or [SELFIES](https://resources.wolframcloud.com/PacletRepository/resource...), but for EVM Blockchain executions.

New comment by spennant in "6NF File Format"

spennant — Thu, 04 Sep 2025 01:42:39 +0000

Odd seeing this right now for me. I recently implemented a 6NF schema for parsed XBRL files from EDGAR. The architecture was the right call... too bad the data is not useful for analytics.

New comment by spennant in "Geocities Backgrounds"

spennant — Wed, 23 Jul 2025 18:16:58 +0000

What? No love for Perl scripts in cgi-bin/ ?

New comment by spennant in "uv: An extremely fast Python package and project manager, written in Rust"

spennant — Mon, 23 Jun 2025 19:16:48 +0000

I moved from pip to poetry a while back, but was introduced to uv recently while working on MCP stuff. I now use uv for everything and haven’t looked back.

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 23:36:53 +0000

It's coming...

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 15:51:36 +0000

Just a fancy way of saying that multiple agents (with their own LLMs) can concurrently connect, also that pg-mcp can simultaneously connect to multiple Postgres servers as well.

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 15:48:15 +0000

The use case for pg-mcp is server deployment - local running is just for dev purposes. HTTP/SSE enables multiple concurrent connections and network access, which stdio can't provide.

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 15:11:09 +0000

Xata.io looks very interesting!!! I was thinking about building an intelligent agent for pg-mcp as my net project but it looks like you did a lot of the hard work already. When thinking about the "AI Stack" I usually separate concerns like this:

  UI <--> Agent(s) <--> MCP Server(s) <--> Tools/Resources
             |
           LLM(s)

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 14:57:28 +0000

Indeed. Anything you do with MCP can be done in more traditional ways.

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 14:31:16 +0000

I built this to fill a specific need. It's not really made to talk to Claude Desktop (although it can). It's built to take multiple connections from agents who bring their own LLM (via API key or whatever) and provide context to the LLM model. Yes, it does import the standard Python MCP package, however it does quite a few non-standard things in order to achieve the multi-tenancy. I encourage you to look at the code.

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 12:27:57 +0000

I made a few assumptions about the actual deployer and their environment that I shouldn’t have… I’ll need to address this. Thanks!

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 12:18:24 +0000

The pg-mcp server doesn’t need an API key. Those variables are only needed to run the example claude-client. You can write your own agent to talk to whatever LLM you like.

New comment by spennant in "Show HN: Cloud-Ready Postgres MCP Server"

spennant — Sun, 30 Mar 2025 12:10:50 +0000

It won’t be that easy. First off, most databases in the wild are not well documented. LLMs benefit from context, and if your tables/columns have non-intuitive or non-descriptive names, the SQL may not even work. Second, you might benefit from an LLM fine-tuned on writing code and/or an intelligent Agent that checks for relevancy and ambiguity in user input prior to attempting to answer the question. It would also help if the agent executed the query to see how it answered the user’s question. In other words “reasoning”… pg-mcp simply exposes the required context for Agents to do that kind of reasoning.