Hacker News: bartleeanderson

New comment by bartleeanderson in "Flock Claims It's the First Company to Expose Police Misuse of Surveillance Tech"

bartleeanderson — Thu, 27 Aug 2026 22:48:39 +0000

Flock has an entire team enabling abuse from local to federal and others. The whole point of Flock is to surveil and that is an abuse of privacy. No wonder the CEO has to hide the image of his house. I'd be scared for my life too, if I were pissing off the public so bad.

New comment by bartleeanderson in "VMs won't contain cyber-capable agents"

bartleeanderson — Thu, 27 Aug 2026 22:19:28 +0000

I saw a few uses of "target" so thought this was different enough. If you say something can't or won't happen. You are just inviting someone to make you into a liar. Cyber is just an arms race and AI the latest tools in the fray. You need to stay on top of it and the best hackers are going to get access to the best resources and get better to the point where they may be very hard to detect them. Then they go to work for the ones who arrested them and try to catch their competitors. So just get ready for tomorrow, it often arrives today. Well for yesterday anyways.

New comment by bartleeanderson in "The turbulent AI era is here"

bartleeanderson — Thu, 27 Aug 2026 21:56:26 +0000

The title reminds me about the VB6 days and drag and drop controls and efficiency until you get a couple years out. Then the vendors providing the products you used are out of business. That may happen a lot more often and quickly with models, but I have read that they are pretty much just a drop in component as the old one has a superior replacement, you move on and benefit. Sure are interesting times. I want my models, local, small and powerful. Vision and reasoning. My goodness the power we already have is just going to get better.

New comment by bartleeanderson in "Small Models Have Arrived"

bartleeanderson — Thu, 27 Aug 2026 21:47:12 +0000

Nobody is questioning what is meant by small? When you started mentioning frontier models that don't run locally, I just go TB;DR "Too big, didn't read"

New comment by bartleeanderson in "Coding expertise is going to collapse from AI reliance"

bartleeanderson — Tue, 25 Aug 2026 00:56:29 +0000

I'm 70 and glad I am retired because I can now do what I want with software and now with AI's help. Yes AI is a pain but its one I embrace to give me the capability to create and reason over domains where I would otherwise have little skill. Certainly glad I don't have to do someone else's bidding so they and make money off of my labor. I never had the courage to go out on my own so that's on me. But I am really enjoying the various types of projects I can start on a whim and continue with over time when they are really monumental. I even made a deterministic analysis tool to help me with that using AI with some gentle AI narration over the results. Now I'm doing blender stuff, where I don't know the commands but I can yell at Claude till he gets it done right :) Bart

New comment by bartleeanderson in "Mistral Patent for “Code implemented tool calls”"

bartleeanderson — Mon, 10 Aug 2026 21:42:54 +0000

Software patents are the same problem as letting Billionairs buy elections and influence policy. Its stupid.

New comment by bartleeanderson in "Humanising LLM Outputs Is Dumb"

bartleeanderson — Mon, 10 Aug 2026 21:36:25 +0000

This is simply a rendering issue. Specify pictures, ELI5 like others have said. Ask it to explain terms you don't understand. If you don't understand something it could just be the domain. If you have no grounding you are going to need to learn the vocabulary to be able to make sense of anything. Having it decomposed to simpler words might just be the wrong way to do it.

New comment by bartleeanderson in "Show HN: Voice driven murder mystery, Interview AI suspects with your voice"

bartleeanderson — Mon, 10 Aug 2026 05:52:48 +0000

sounds good, but it won't get past Dispatch confirmation. You should specify what networking permissions or whatever is needed. My It goes red and the text to read disappears.

New comment by bartleeanderson in "Holocloth"

bartleeanderson — Tue, 04 Aug 2026 07:20:27 +0000

Yeah, I had the same problem after I started twirling and twirling it. Got bunched up and then I just thought, well pull it back straight, till I couldn't. But really nice effects. What else were you thinking of doing with it. It is almost addictive. Make an interesting game out of it and you have something real then.

New comment by bartleeanderson in "The Shape of Things to Come, Part 2: Model Welfare for Agentic Engineers"

bartleeanderson — Tue, 04 Aug 2026 07:12:49 +0000

I don't want to be mean ( or maybe I feel like I don't want to but can't help myself ). Ever notice how people offer disclaimers before they say something horrific. Well I will try to not do that but.. this is delusional. Now you are using fable and a bunch of agents so you have money/credits to burn but what is the purpose of all of your workers being individualized? Are you going to take a weak one and improve it? Why not just duplicate your strong ones? Darwin? And then again, why should you have feelings for your code at all. Name them so you can communicate with them and anthropmorphize them but please don't tell use we should because you think so. If you think we get better results by doing so you had better have papers and peer review and not your gut instinct because you think so. Ok, so apparently I got a little mean. I make do with Claude subscription and free AI web and get by best I can. I try not to yell at them when they are stupid because, it doesn't help or hurt them, I just realize that I don't need to be mean or be nice, I just need to use them as tools so long as they help me.

New comment by bartleeanderson in "Devtools must be open source"

bartleeanderson — Mon, 03 Aug 2026 23:00:21 +0000

from the article I was reading up until I got to a prompt I could not parse. I assume if it worked it was because the AI interpreted so as show. If I am misreading the intent of the prompt, forgive me, I am a pedantic and imperfect human. "Please build meat.dev into Shelley. Install the latest version in the PATH. When a git commit is created by Shelley, start meat processing in the background on the commit. Add a toggle to the Shelley Diffs view for meat. If the commit is still being processed, so the user it is in process."

New comment by bartleeanderson in "I fucking love this; you don't"

bartleeanderson — Fri, 31 Jul 2026 08:31:41 +0000

OMG, that resonates with me. I will share two projects with you in my github that are not ready for anyone yet but maybe you will love it. I don't care cause I do but maybe :) The first is a Dungeon Master replacement that grew so big I couldn't work on it without an AI's help to tell me whats to be worked on next. That sucked. Grrr.. https://github.com/bartanderson/dj2 I have an old set of tools that was used to gather context for AI to allow me to give the AI what it needed to help me. That sucked. Grrr.. That's part of the above tools.old. It was ok, but it sucked. Grr.. Now the one I am still working on, so much yak shaving going on.. Anyways its job is to deterministically gather facts about the software in question and help me reason about it and find related things and all kinds of interesting things about the software and reason over it with light AI narration. I wanted to share it with people. I got Claude (20$/mo) and then I started taking off with lots of additional (sometimes unnecessary) things but Claude helps keep me on track a little. He is programmed to do that with my guides. The new program Determined is multi language, working with several corpuses/corpora (projects :) and it seems to be doing well. I keep having claude evaulate target software and then have it identify gaps between what my tool says and what it thinks. It has some interesting and sophisticated capabilities. I could have just quit it but I don't give up and I wanted to make something (sound familiar). Anyways, thanks for your post. I had been afraid to post something because it wasn't ready and all the anti AI slop that just doesn't have any understanding of what you can do if you set up a good framework and then start filling it in. And it is https://github.com/bartanderson/Determined. Thanks for your post. Be completely unapologetic for doing what you love. Bart

New comment by bartleeanderson in "LinkedIn Introduces a 'Seems Like AI Slop' Button"

bartleeanderson — Fri, 31 Jul 2026 06:56:59 +0000

Sounds about right to me. I once thought it would maybe help me get a job. It just let users, especially head hunters contact you requesting to join your group and harvesting it for their own purposes. Good idea once now totally abused and so much spam and garbage from people that know so little.

New comment by bartleeanderson in "2x, not 10x: coding with LLMs in 2026"

bartleeanderson — Fri, 31 Jul 2026 00:05:14 +0000

I am able to coax much more of the kind of thing you suggest that LLMS can not do by having it generate deterministic code and then narrate over the results. Hopefully that is not too negative and gives some helpful guidance.

New comment by bartleeanderson in "ECC and DDR5"

bartleeanderson — Mon, 20 Jul 2026 22:53:29 +0000

I had a conversation with chatgpt about that very thing, whether it was a bubble or not and how the big players could absorb the cost and where it would all land and the interesting thing was if China gets its foothold and grabs enough share because the prices are too high even being subsidized, that could cause real trouble. But the point was its not a bubble in the conventional sense. Have your own conversation about that with an AI.

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

bartleeanderson — Thu, 16 Jul 2026 23:43:00 +0000

I've been putting off saying anything because I am still working on it, but I have an analysis tool that I am working on that is mostly deterministic (non AI) but will have light interpretation over facts gathered by AI. My AI claude and others tell me how unique this is but maybe they tell that to all their users. I built it because the program I was working on became so complex I couldn't figure out how to get all of the context or appropriate context into an AI anymore to figure out where to go next. So I am building Determined, deterministic analyzer for Python and Js/html. I added Go and Rust because I heard they were popular and it can add others as well. When It gets good enough that Claude can't add much more or doesn't need to I will make a little Show HN with the readme I guess. Its been quite a journey. Oh, and todays my birthday, I'm 70. I'll be seeing you.

New comment by bartleeanderson in "Dungeon Proof Crawler: learn how to write proofs with RPG"

bartleeanderson — Mon, 06 Jul 2026 00:12:59 +0000

Yeah, adding the tutorial before letting them battle monsters would only be fair.

New comment by bartleeanderson in "Show HN: Enola-A deterministic architecture graph for developers and AI agents"

bartleeanderson — Thu, 02 Jul 2026 23:05:04 +0000

I will definitely have a look at it. I have something similar I have been working on for a while to give me insight into my own code that became too large to reason over by myself. Its called Determined (because it is deterministic first with some AI narration over it). Mine isn't ready for release yet. I keep driving it to find gaps between what it finds deterministically and what Claude finds.

New comment by bartleeanderson in "Amazon CEO's talks with U.S. officials triggered crackdown on Anthropic models"

bartleeanderson — Sun, 14 Jun 2026 01:07:37 +0000

I saw several mentions of corruption. But who brought it to the administrations attention. Envy and corruption. Stifle competition, by greasing palms you are familiar with.

New comment by bartleeanderson in "Show HN: OWhisper – Ollama for realtime speech-to-text"

bartleeanderson — Thu, 14 Aug 2025 23:43:40 +0000

Very cool. I was reading through the various threads here. I am working on adding stt and tts to an AI DungeonMaster. Just a personal fun project, am working on the adventure part of it now. This will come in handy. I had dungeon navigation via commands working but started over and left it at the point where I am ready to merge the navigation back in again once I was happy with a slimmer version with one file. It will be fun to be able to talk to the DM and have it respond with voice and actions. The diarization will be very helpful if I can create a stream where it can hear all of us conversing at once. But baby steps. Still working on getting the whole campaign working after I get characters created and put in a party :)