Hacker News: cjonas

New comment by cjonas in "Training our own AI models"

cjonas — Wed, 27 May 2026 16:46:12 +0000

yea except one is a "dark pattern" to exploit customers for corporate profit while the other is to benefit society.

New comment by cjonas in "Show HN: Id-agent – Token efficient UUID alternative for AI agents"

cjonas — Tue, 19 May 2026 14:27:47 +0000

Not sure I understand. If you generate a random string to use as a reference for something that the LLM interacts with... and the LLM cannot reliably recall the reference, then it's a problem that needs to be solved by simplify the random string.

New comment by cjonas in "Show HN: Id-agent – Token efficient UUID alternative for AI agents"

cjonas — Tue, 19 May 2026 12:55:41 +0000

The problem is really more getting the agent to reliable relay a UUID. For example, we were creating files for visualizations and having the agent reference them in there response with a custom and found that it would often fail to accurately return a UUID from a tool response it was previously provided (running sonnet 4.6).

For this use case, our solution was just to use a slug for the filename, but we can control the uniqueness constraint on our backend.

New comment by cjonas in "δ-mem: Efficient Online Memory for Large Language Models"

cjonas — Sat, 16 May 2026 15:50:19 +0000

Coding agents don't really need memory. Agent skills, rules, git history, documentation is all far more efficient, transparent and easier to manage. These memory frameworks only really makes sense if you are building a consumer facing agent with managed context and limited capabilities.

New comment by cjonas in "VS Code inserting 'Co-Authored-by Copilot' into commits regardless of usage"

cjonas — Sat, 02 May 2026 23:54:55 +0000

Claude code not supporting specifying an alternate location to look for agent skills is another example.

New comment by cjonas in "Incident with multple GitHub services"

cjonas — Fri, 24 Apr 2026 02:51:58 +0000

this is fair. I should have just said "Site Reliability", as it's almost certainly out of the engineers control.

New comment by cjonas in "Incident with multple GitHub services"

cjonas — Thu, 23 Apr 2026 17:07:42 +0000

also I never had considered that breaking your up-time into a bunch of different components is just a strategy to make your SRE look better than it actually is. The combined up-time tells the real story (88%!). Thanks for the link

New comment by cjonas in "Incident with Multple GitHub Services"

cjonas — Thu, 23 Apr 2026 16:57:13 +0000

ya i was just doing the math on their chart for the git operations. I added up 14.93 hours combined hours, which puts them WAY lower than the reported 99.7 metric they show right next to it.

So based on their own reporting, the uptime number should be 99.31. Which means only like 6 additional hours and they'd fall below 99.0%

New comment by cjonas in "Incident with multple GitHub services"

cjonas — Thu, 23 Apr 2026 16:50:13 +0000

It would be wild if they dropped below the "two 9's" metric. I think they would need an additional ~16hr of outage in the 90 day rolling period.

New comment by cjonas in "Ask HN: How did you land your first projects as a solo engineer/consultant?"

cjonas — Sun, 19 Apr 2026 12:25:07 +0000

Whats your actual tech experience?

Most enterprises that need consultants are using Salesforce, SAP, Hubspot, Dynamics, etc. If a company has an engineering department to build and run internal software, they very rarely need a consultant. And if they don't, they are very unlikely to higher a consultant to build it custom. They'd want "out of the box" because they think (often incorrectly these days), it will be easier to maintain.

New comment by cjonas in "Pro Max 5x quota exhausted in 1.5 hours despite moderate usage"

cjonas — Sun, 12 Apr 2026 23:00:56 +0000

These days cursor feel more capable and reliable then Claude Code (at last for my workflow). For personal projects, I'm using cursor during planning and verification but run Claude code for just implementation to save $.

New comment by cjonas in "Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage"

cjonas — Sun, 12 Apr 2026 14:14:48 +0000

Ya I've had this experience more than a few times recently. I've heard people claiming they are serving quantized models during high loads, but it happens in cursor as well so I don't think it's specific to Anthropics subscription. It could be that the context window has just gotten into a state that confuses the model... But that wouldn't explain why it appears to be temporary...

My best guess is this is the result of the companies running "experiments" to test changes. Or it's just all in my head :)

New comment by cjonas in "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter"

cjonas — Fri, 10 Apr 2026 04:26:38 +0000

Wouldn't they be using the Azure inference API or AWS bedrock on their own accounts and NOT be going through the openAI/Anthropics servers anyways? I just always assumed this is how the big inference "resellers" (openrouter, cursor, etc) were operating.

New comment by cjonas in "Show HN: Stop paying for Dropbox/Google Drive, use your own S3 bucket instead"

cjonas — Tue, 07 Apr 2026 13:30:37 +0000

Why does getting started have me sign up for an account vs take me to the docs to self host?

New comment by cjonas in "We rewrote JSONata with AI in a day, saved $500k/year"

cjonas — Thu, 26 Mar 2026 23:18:27 +0000

The docs indicate there are already 2 other go implementations. Why not just use one of those? https://docs.jsonata.org/overview.html

New comment by cjonas in "Show HN: A plain-text cognitive architecture for Claude Code"

cjonas — Thu, 26 Mar 2026 13:44:43 +0000

Honestly memory seems like an overcomplicating way to solve this problem in the context of something like a coding agent. Rules and Skills are much more explicit, less noisy and easier to maintain. Just requires having an always on rule/system prompt to always update rules/skills as designs or architecture changes in a way that conflicts with old rules. Memories maybe make more sense for personal assistant use cases.

New comment by cjonas in "No-build, no-NPM, SSR-first JavaScript framework if you hate React, love HTML"

cjonas — Tue, 24 Mar 2026 13:49:53 +0000

This is basically "reactive UI" foundation. The complexities come from effects (now managed via hooks)

New comment by cjonas in "We give every user SQL access to a shared ClickHouse cluster"

cjonas — Sat, 21 Mar 2026 14:42:04 +0000

Small. We're dealing with financial accounts, holdings and transactions. So a user might have 10 accounts, thousands of holdings, 10s of thousands of transactions. Plus a handful of supplemental data tables. Then there is market data that is shared across tenants and updated on interval. This data is maybe 10-20M rows.

Just to clarify, the data is prepared when the user (agent) analytics session starts. Right now it takes 5-10s, which means it's typically ready well before the agent has actually determined it needs to run any queries. I think for larger volumes, pg_duckdb would allow this to scale to 10s of millions rows pretty efficiently.

New comment by cjonas in "We give every user SQL access to a shared ClickHouse cluster"

cjonas — Sat, 21 Mar 2026 13:57:34 +0000

We have various data sources (which is another benefit of this approach). Data from the application DB is currently pulled using the FE apis which handle tenant isolation and allow the application database to deal with the load. I think pg_duckdb could be a good solution here as well, but haven't gotten around to testing it. Other data come from analytics DB. Most of this is landed on an interval via pipeline scripts.

New comment by cjonas in "How we give every user SQL access to a shared ClickHouse cluster"

cjonas — Sat, 21 Mar 2026 13:42:59 +0000

Idk but I named everything in the related code "duckpond" :)