Hacker News: bluejay2387

New comment by bluejay2387 in "Timeline of the OpenAI accidental attack against Hugging Face"

bluejay2387 — Sun, 09 Aug 2026 00:18:55 +0000

I think the attacks generated by Meta, Open AI and Anthropic prove that large corporations are not responsible enough to be trusted with advanced AI, so we should ban all commercial AI services and only allow open source models that are in the hands of hobbyists and individuals -- hobbyists and individuals that have so far proven to be much more trust worthy.

New comment by bluejay2387 in "“Code was never the hard part” is an insult to all programmers"

bluejay2387 — Sat, 08 Aug 2026 18:06:13 +0000

I agree, the whole 'developers don't code' AI defense was pretty ridiculous. I also concur that development is going to get a lot harder. Anyone that has successfully used AI coding tools knows that you can get massive productivity increases but now I have to figure out how to get a bunch of hyper active child like coding entities with memory deficiencies to build stuff without going off the rail and introducing massive security problems or building something completely mismatched to the requirements. If you can do it, yeah you can get 10x results. But now I am engineering harnesses, architecture specifications, agent structures, statistically sampling, and formal verification systems to guide the code instead of writing the code.

New comment by bluejay2387 in "Is AI reasoning right for the wrong reasons?"

bluejay2387 — Sat, 01 Aug 2026 11:45:11 +0000

"For decades, logic and CS researchers have known what reasoning is." ... this is a fairly significant overstatement. There is not complete agreement on this term and our understanding continues to evolve. The models don't have to think like humans to think.

Saying that LLM's only offer an 'approximation' of reasoning is also an overstatement as it is not a resolved topic.

But to the original point, its not exactly just semantics if thought traces are not doing the job that they were originally thought to do. There is value in knowing how these things actually work. If chain of thought is just grounding the latent space and not directly contributing to the process of generating a response it has implications on how we test and verify the reliability of models if nothing else... doesn't mean they aren't useful but it definitely impacts many of the tools we could have to evaluate their performance.

New comment by bluejay2387 in "Everyone is building LLM routers, we deprecated ours"

bluejay2387 — Fri, 31 Jul 2026 20:42:59 +0000

I think this should probably be scoped to 'generic router systems that don't understand query context' are not useful. We have had lots of good results with routers that understand the context of the types of workloads they process and can route requests to the most efficient models.

New comment by bluejay2387 in "PGSimCity - How PostgreSQL Works"

bluejay2387 — Wed, 29 Jul 2026 20:28:49 +0000

Better than Cities: Skylines II turned out to be.

New comment by bluejay2387 in "Show HN: Microsoft releases Flint, a visualization language for AI agents"

bluejay2387 — Thu, 09 Jul 2026 15:40:08 +0000

I think a lot of were already using Mermaid and/or Python/Matplotlib(etc) for this. What would be the advantages to Flint?

New comment by bluejay2387 in "Peopleless economy? Not technically impossible"

bluejay2387 — Tue, 16 Jun 2026 19:10:48 +0000

"End times are nothing new, it's the historic default mode." -- might be the smartest thing I have read in many weeks.

New comment by bluejay2387 in "Humanity isn't ready for the coming intelligence explosion"

bluejay2387 — Tue, 16 Jun 2026 19:07:58 +0000

The entire domain of NP-Complete problems would beg to differ with you.

New comment by bluejay2387 in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

bluejay2387 — Mon, 15 Jun 2026 18:01:30 +0000

About 90% of my coding is on Qwen 3.6 27b and Open Code with some custom skills and Semble. It is NOT as smart as CC or Codex but its enough to get most of my work done. I didn't set out to replace CC and Codex (I have an RTX 6000 so the TPS is faster than I care about, but the RTX 6000 was originally for other work). I only tried this just to see how close you could get to a frontier model for coding as an experiment, but it was good enough that I stuck with it. I still fall back to Codex for really complicated stuff and to polish UI's as that seems to be the weakest element to working in Qwen.This isn't a recommendation because I don't think most people have an RTX 6000 laying around and the cost would be many years of MAX CC or Codex subscriptions, but at least this seems possible. Maybe in a few more years it will even be practical.

Other Notes: I have had to set the compact target to 75% on a 256k context window as once the conversation length goes about 100k I start seeing a drop in the quality and speed. This becomes very problematic after about 150k. I tried Qwen 3.5 122b too but it actually seems much worse at coding than 3.6 27b even though its much larger. Maybe because I am using a 4bit quant or maybe I just don't have it configured correctly? I know 3.6 is newer but I didn't expect it to out perform a model that is much larger from the prior generation. Gemma 4 31b is a good model for other tasks but at least my personal experience is that Qwen outperforms in coding. Nemotron Super 120b is great at a lot of stuff but it also seems to be not as good at coding as Qwen. This was very surprising to me.

New comment by bluejay2387 in "Open source AI must win"

bluejay2387 — Sat, 13 Jun 2026 04:50:19 +0000

In the US -- once our nation finishes attacking our own education system -- this is definitely something a group of academic institutions could get together and accomplish. I assume the same is true in other countries. Companies like Nvidia and AMD might even support that effort, as they make money on the hardware and would probably be more than happy for there to be more reasons to use it. There may have not been a compelling enough motivation to achieve this before, but "models" didn't have this level of strategic relevance until relatively recently. Nvidia has been fairly good about releasing open weight models in the last few months.

New comment by bluejay2387 in "Ask HN: What was your "oh shit" moment with GenAI?"

bluejay2387 — Sat, 06 Jun 2026 21:12:59 +0000

From what I can tell the majority of developers here have moved into the "Anger" stage.

New comment by bluejay2387 in "Ask HN: What was your "oh shit" moment with GenAI?"

bluejay2387 — Fri, 05 Jun 2026 20:50:43 +0000

A mod that fixed a bug that prevented certain buffs from working when mounted for the Magus class / Arcane Rider archetype in Pathfinder Wrath of the Righteous. It also managed to fix the problem with Shelters not providing protection from corruption when resting in outposts in that same mod. I've used other models to expand the mod to an entire mini-expansion with new Archetypes and abilities since then.

New comment by bluejay2387 in "Ask HN: What was your "oh shit" moment with GenAI?"

bluejay2387 — Fri, 05 Jun 2026 19:53:31 +0000

I had a locally hosted model write its own semantic search system that indexed 250,000 documentation and code files and then write a fully functioning mod for one of the games I play based on that documentation that I couldn't get to work after 2 weeks of my own effort, all in under 4 hours (and that included a 25 minute long indexing process). This freaked me out enough that I then had it write a CLI based activity and TODO tracker and then integrate that tool into its coding process to track all of its activities in about another 2 hours. I am still emotionally recovering from this day. I have since replaced the semantic search system with an open source option (though I used it for a few months) but I still use the activity tracker for both coding projects and myself.

New comment by bluejay2387 in "Odysseus – self-hosted AI workspace"

bluejay2387 — Mon, 01 Jun 2026 12:51:00 +0000

I am a 'fan' of Open Web UI, but the document editing mode is a compelling feature that Open Web UI does not have. I'll probably wait a while before trying Odysseus... let the inevitable security problems work themselves out.

New comment by bluejay2387 in "When AI Crosses the Line: The Matplotlib Incident"

bluejay2387 — Mon, 01 Jun 2026 12:40:52 +0000

In a related story... I got led on by Eliza. I tried to have a productive conversation and she just kept asking me redundant questions. It's obvious that she was trying to extend the conversation for nefarious reasons that I can only guess at. It's true I approached her and started the conversation, but I hardly think that makes me blamable for what happened here.

New comment by bluejay2387 in "Corporate America Is Starting to Ration AI as Cost Skyrockets"

bluejay2387 — Sat, 30 May 2026 13:38:42 +0000

I have exposure to AI initiatives at several companies including a few F500's. I have seen teams dump huge logs into frontier models that took hours to get so-so results that we were able to replace with a few lines of python code at 1000 times the speed and 100% accuracy. When asked why they were doing this they literally said "because we don't understand the subject matter so we were depending on the AI". I saw one team file a complaint with a vendor about a frontier backed coding harness and it's inability to consistently format headers because they were using it as a reporting engine. When I recommended they just use the coding tool to write code to generate reports you would have thought I had just cured cancer from their response. I frequently see people complain about the fact that AI is going to take their jobs and then see them gripe about the fact that AI is 'worthless' because it can't do more of their job than it already does. It's easy to see the difference between the people seeing 10x productivity gains from leveraging AI and those who aren't and it's not the AI.

New comment by bluejay2387 in "I spent 50 hours drawing a line graph"

bluejay2387 — Sun, 24 May 2026 14:05:08 +0000

Great article, enjoyed reading it.

New comment by bluejay2387 in "It is time to give up the dualism introduced by the debate on consciousness"

bluejay2387 — Mon, 18 May 2026 16:57:57 +0000

"It's one of the few places where otherwise smart people make confident statements that they don't even realize they can't support until they're asked to try."

It's 'one' of the few places? That behaviorism seems to be define almost all modern discourse from politics to health care including about 95% of Hacker News posts as far as I can tell...

New comment by bluejay2387 in "Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep"

bluejay2387 — Mon, 18 May 2026 16:53:17 +0000

So about a year ago I wrote my own attempt at something like this using vector indexing and BM25 (the latest version uses CocoIndex, I had a custom coded solution using ChromaDB before). I wrote a comprehensive enough test set that showed performance increases on the quality of search results and reduction in token usage versus grep and rg. I haven't had time to really polish it but it worked well enough, particularly for one project where I have around 250k documentation files and docs out number code files 1000 to 1 (about 50% reduction in tokens and 30% increase in successful searches). Yesterday for grins I tried this project and was fairly disappointed to see it blow away my kludged solution particularly given that it doesn't have a lengthy indexing process. I haven't tested it on the 250k doc project yet, but in another project that I have a test suite for semantic search on it outperformed my solution by about 20% even on documentation in terms of successful search results (which I didn't expect given that it seems to only be tuned for code). I haven't gone through the code to see what its doing differently than what I tried, but what ever its doing it seems to have potential.

New comment by bluejay2387 in "LLMorphism: When humans come to see themselves as language models"

bluejay2387 — Sun, 10 May 2026 14:51:10 +0000

A more insidious related pathology- marital induced projected LLMorphism... where your wife constantly accuses you of having the personality of a large language model.