Hacker News: cjonas

New comment by cjonas in "A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost"

cjonas — Sat, 07 Nov 2026 00:26:12 +0000

you can easily run qwen locally in a pi harness (or similar) and just tell claude code to delegate all implementation work to it. claude will even setup the harness with the local model

New comment by cjonas in "OccupySaaS"

cjonas — Mon, 02 Nov 2026 13:26:40 +0000

I like what artcraft is doing with adobe, but a 1-to-1 clone of Salesforce is not as compelling. There are so many bad product and technical decisions baked in... Ideally you'd be building something better from the ground up (linear vs jira).

Also, why target multi-tenant? presumably the audience is a single org.

New comment by cjonas in "Postgres 19 is late because so many more bugs are being found now"

cjonas — Mon, 02 Nov 2026 12:24:50 +0000

in theory, a company running custom software should be able to invest many more hours into running those same AI with "white-box" pen-testing (assuming hyperscalers actually start allowing this). An attacker would have to be willing to outspend the company (or get very lucky). If an attacker is resourced well enough to put that investment into owning a single company, you probably don't stand much chance reguardless.

New comment by cjonas in "Claude Duet"

cjonas — Thu, 22 Oct 2026 02:46:33 +0000

i did this with opus5.5 this year and it caught an 8000$ mistake. Obviously i should find a new CPA, but i have found it incredibly helpful. One downside is that it will likely also flag a bunch of "by the book" libilities to how your filing that I'm pretty sure most CPA would let slide.

New comment by cjonas in "Gemini 4 Argon"

cjonas — Wed, 14 Oct 2026 15:46:47 +0000

My first experience in antigravity was extremely disappointing.

I asked for a QUICK healthcheck on the sync status of a bigquery integration. It literally spun for 25m before I killed it.

The task, which is CLEARLY outlined in the agent readmes just involved using the gcloud cli to initiate auth, then just run a few queries to check logs and timestamps.

Even 3.6 flash can get this right (most the time).

New comment by cjonas in "GPT-6 Astra Helped Me Jailbreak My Kindle"

cjonas — Tue, 13 Oct 2026 01:08:12 +0000

I wanted to do this with a google home hub so i can run my own fully local "home assisant", but claude rejected it... instead i ordered a used lenovo thinkview device which appetently has a community around custom bootloading...

But it does make you think there might be a real market for unlocked devices like this now that it is trivial to build your own software to do exactly what you want.

New comment by cjonas in "Doory – Open-Source Canva"

cjonas — Mon, 12 Oct 2026 14:15:34 +0000

I think that sould be obvious without even looking at the code... Like what artcraft did with adobe, its now viable to offer apps completely free by leveraging 100% ai. You could argue the code quality doesnt matter much as long as it works (for local apps security is less a concern).

Also, when building similar style apps, I often don't even start git until the app is in a stable state. The earliest code is often worthless and the overall direction not stable.

New comment by cjonas in "Show HN: BetterWispr – Free, open-source dictation for Mac"

cjonas — Sun, 11 Oct 2026 16:54:31 +0000

i forked handy and built 2 modes. One for dictation and one for quick agent actions that uses the pi harness with local models and jev style classifiers so it can read screens and interact with elements (via accessiblity tree, screenshots, os scripts, bash, mcp, etc). Its nice because in agent mode you can just give it instructions on how to respond (like dictation that can read the context of the current page or input). I've been pretty happy with it so far and debating if i should release it. Just not sure if the world needs yet another vibe coded agent system.

New comment by cjonas in "ArtCraft Apps – open-source Adobe compatible suite written in Rust"

cjonas — Mon, 05 Oct 2026 01:43:47 +0000

Despite whatever else happens with AI, I am excited about the near future where we have an open source version of basically every app. I hope this is the beginning of the end of the subscription model. Keep it up!

New comment by cjonas in "Sites in ChatGPT"

cjonas — Fri, 02 Oct 2026 20:59:09 +0000

Once everyone operates as you do, then websites will have little value. Just publish a .md file or API if you have interactivity.

New comment by cjonas in "America.gov"

cjonas — Tue, 29 Sep 2026 21:41:55 +0000

This thing is obviously fully vibe coded... Click the "what's coming next" and under the healthcare section the marketing screenshot contains broken images... Like no one ever looked at this before deploying it?

New comment by cjonas in "Show HN: Jev Plays Pokémon Red"

cjonas — Sat, 26 Sep 2026 14:18:19 +0000

Where does the "goal" come from? Is it just known based on different positions in the game? Otherwise it seems like it would require text generation.

New comment by cjonas in "Ollaya – Ollama for open-source, Jev-style decision models"

cjonas — Sat, 26 Sep 2026 06:47:37 +0000

I've been testing, for my use case laya didn't come close to decider was just as good. My experience with the 3 models matches the result here

https://benchmarkheaven.com/jev-models

New comment by cjonas in "Ollaya – Ollama for open-source, Jev-style decision models"

cjonas — Sat, 26 Sep 2026 06:44:23 +0000

Is it likely not just distilled from one of the flagship models? That sounds like an afternoon of work and a few thousand dollars in tokens?

New comment by cjonas in "Grok 4.7"

cjonas — Tue, 22 Sep 2026 02:26:15 +0000

I agree there is probably some impact on output quality when doing this (Claude seems to embedded key signals all over the writing, which is much or what makes it horrible to read). However this does work well as a "second pass" over technical docs or designs along the way

New comment by cjonas in "Tin: full-text search for Postgres"

cjonas — Sat, 19 Sep 2026 16:35:25 +0000

Seems like a lot of this knowledge was encoded into the blog post. I wonder if given this post and access to a planet scale instance to compare with, how close an agentic agent could get.

New comment by cjonas in "Claude Code now reads AGENTS.md if there is no Claude.md"

cjonas — Sat, 19 Sep 2026 00:09:27 +0000

Meanwhile, I just setup codex for the first time (to try Astra) and it offered to load my Claude and Cursor conversations and claims to even do it in a way where it says in sync if you use both. The only reason to use Claude Code is the 20x usage of the 200$ plan is ridiculous value if you have the need for that volume.

New comment by cjonas in "iPhone Duo"

cjonas — Wed, 09 Sep 2026 18:40:55 +0000

I don't follow iphone products, but if it's anything like android this is because they tend to be the lower end models and are missing the features that people really want (mainly a better camera/lens setup). The top of the line models are ALWAYS the bigger phones and if your going for something budget, then you're better off with the Chinese brands for value.

New comment by cjonas in "Ask HN: Who is using MCP in production?"

cjonas — Fri, 04 Sep 2026 05:54:02 +0000

We use mcp as a "gateway" for a customer facing cloud agent. It basically is just a tool registry and could have been built using open-api... but MCP is arguably more robust/aligned for context management and the agent frameworks and observability tools support it first class.

New comment by cjonas in "METR and Redwood Offer Holy %^ Postmortem of the HuggingFace Hack"

cjonas — Sun, 30 Aug 2026 18:55:02 +0000

All it would have taken is someone to peak at the output tokens during the run and it would have been obviously the test had gone off rails.