Hacker News: gbro3n

New comment by gbro3n in "Don't trust large context windows"

gbro3n — Sun, 14 Jun 2026 17:40:18 +0000

Thanks, those don't deterministically prevent the main loop from using tools thought, unless I'm wrong that's just prompting the main agent on when to use specialized sub agents

New comment by gbro3n in "Ask HN: What are you working on? (June 2026)"

gbro3n — Sun, 14 Jun 2026 17:33:55 +0000

https://www.asnotes.io - a Foam / Dendron / Obsidian / Logseq alternative with tasks, kanban board, static site publishing for VS Code

https://www.agentkanban.io - Github Copilot / Claude Code integrated Kanban board with context management

https://www.asmusictheory.com - Music Theory lessons, tools, including piano roll with midi in the web browser

New comment by gbro3n in "Don't trust large context windows"

gbro3n — Sun, 14 Jun 2026 09:44:48 +0000

This makes intuitive sense. Can I ask what harness you're using that allows you to configure the constraint and how?

New comment by gbro3n in "Ear Training Practice"

gbro3n — Fri, 12 Jun 2026 11:27:20 +0000

Thank you. Any feedback would be greatly appreciated :)

New comment by gbro3n in "Ear Training Practice"

gbro3n — Fri, 12 Jun 2026 10:56:53 +0000

Thank you, any feedback is appreciated.

New comment by gbro3n in "Ear Training Practice"

gbro3n — Fri, 12 Jun 2026 10:56:04 +0000

Thank you for your feedback - I have it working on iPadOS 26.5 (Chrome and Safari). The browser auto-play policy does require some interaction with the page before it will play (so the first key press is often mute, but should sound after). There is a button on the control bar to enable sound explicitly. I will look for more instances (not to ask the really obvious question, but do you have sound turned up or a bluetooth connection you're not aware of by any chance?). Thanks again

New comment by gbro3n in "Ear Training Practice"

gbro3n — Fri, 12 Jun 2026 06:57:55 +0000

For https://www.asmusictheory.com, I built in a spaced repetition test section to aid memory retention, along with "a free play" mode for when you just want to explore.

New comment by gbro3n in "Ear Training Practice"

gbro3n — Fri, 12 Jun 2026 06:56:31 +0000

Awesome, this is a great resource. I've been working on https://www.asmusictheory.com , which focuses excercises around an interactive onscreen / midi capable keyboard (where it makes sense). I'm building it as I learn myself.

New comment by gbro3n in "[dead]"

gbro3n — Wed, 10 Jun 2026 12:30:01 +0000

Prior to this release, Agent Kanban - the online task board with agent harness integration for task management and context capture worked primarily with Github Copilot. With this release, the extension now supports Claude Code (the VS Code extension or TUI)

New comment by gbro3n in "Ask HN: What are tools you have made for yourself since the advent of AI?"

gbro3n — Tue, 09 Jun 2026 05:28:30 +0000

A music theory learning tool. I'm building bits as I learn new areas - https://www.asmusictheory.com

I also built a kanban board with agent integration and context management, with a vs code extension to go with it (also helps with git worktrees too): https://www.agentkanban.io

There is AS Notes - an Obsidian / Logseq / Roam alternative for use a s a VS code extension (is designed for use behind corporate firewalls, git friendly): https://www.asnotes.io

Also NumeroMoney: https://www.numeromoney.com - For personal finance spending analysis and budgeting.

AI has been a great 'exoskeleton' for me. I fortunately had some good infrastructure and solid application base templates from before AI 'got gud' and so building on these has been the best of both worlds - a solid base and improved speed of development.

New comment by gbro3n in "Job: Head of Stonehenge"

gbro3n — Tue, 09 Jun 2026 04:30:58 +0000

The UK is still the 5th biggest economy in the world. Public infrastructure feels like it's under huge strain however, and there is also a big problem with inequality, which seems to be changing under Labour, albeit slowly.

New comment by gbro3n in "MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second"

gbro3n — Mon, 08 Jun 2026 17:09:25 +0000

This is a great point. LLMs can't speed up human decision processes and alignment.

New comment by gbro3n in "LLMs are eroding my software engineering career and I don't know what to do"

gbro3n — Sun, 07 Jun 2026 13:52:04 +0000

AI is beat thought of as an exoskeleton, you'll be at a huge advantage if you learn how to use it properly, and you will, unfortunately fall behind if you don't. I still think we're going to need people who can reason about code, and the amount of code to reason about is exploding in volume. Think of it as doctors having access to better drugs and techniques - they can can cure more illness, but the bar and expectation of what they can do will just raise. And doctors are still well paid, because what they do is important and needs doing well.

New comment by gbro3n in "OpenRouter raises $113M Series B"

gbro3n — Sat, 30 May 2026 18:58:25 +0000

I've wondered this too - exactly how are our inputs and outputs useful as training data? So I asked Gemini. Apparently using negative sentiment in user or llm responses can serve as RLHF, and the human prompts can also serve as useful data for what problems the llms need to be able to solve. There's also that smaller models can train on and improve from data from larger models but that's less relevant when not switching models in context.

New comment by gbro3n in "You can just say it"

gbro3n — Sat, 30 May 2026 06:05:02 +0000

> A human iteratively (sometimes painstakingly) shapes and reshapes their creation until it sufficiently matches what’s in their mind’s eye. The odd thing about generative AI is that it can produce substantial form with minimally applied intent.

To add - I think attention is the scarce resource on both ends. Was this creation important enough to give it my full attention (i.e. do it my self). Is this creation important enough for the user to use / consume (i.e without an agent interacting with it on our behalf or summarising)

New comment by gbro3n in "Microsoft starts canceling Claude Code licenses"

gbro3n — Sat, 23 May 2026 08:13:16 +0000

But there isn't a copilot model is there? Just a harnesse, and the vscode copilot extension is pretty good (haven't tried the tui)

New comment by gbro3n in "Microsoft starts canceling Claude Code licenses"

gbro3n — Sat, 23 May 2026 08:11:03 +0000

Same, with regard to TUIs in general. The VS code copilot chat extension has really nice integration for 'human in the loop' style agentic development. I build some tooling - https://www.agentkanban.io to integrate a taskboard and git worktrees with copilot chat

New comment by gbro3n in "Open source Kanban desktop app that runs parallel agents on every card"

gbro3n — Fri, 22 May 2026 18:58:20 +0000

There's a few apps out there that facilitate handing off to agents from kanban boards. I needed something more 'human in the loop', handing off to an agent without good visibility of the change set and opportunity to steer doesn't work for me. https://www.agentkanban.io links a taskboard with github copilot chat in vs code via our extension so we have the benefit of task management and context capture from the chat to the tasks. This gives us all the features of a top harness (vs code) and the task / project management features at the same time.

New comment by gbro3n in "Google's Antigravity Bait and Switch"

gbro3n — Thu, 21 May 2026 16:48:20 +0000

I tried antigravity when it was first released, I didn't see an advantage over vscode, which it's forked from, and there were a few extensions I used that aren't supported. I've been a huge fan of copilot in vscode, the tight integration beats the TUI harnesses, and I've built some tooling around it (https://www.agentkanban.io) so I've got an integrated task board, context capture on the board and git worktree management for parallel tasks)

New comment by gbro3n in "We're testing new ad formats in Search and expanding our Direct Offers pilot"

gbro3n — Thu, 21 May 2026 10:51:35 +0000

I won't be able to use their AI results if they are, personally. If I ask the question "what is the best tool for doing x" and I can't trust that the answer is going to be the truth according to all available information, then the AI is useless or worse, misleading. If google is unbiased, and only highlights paid advertiser mentions, no one will pay. I'd only accept this if it was a clear separation of LLM response and ads in a sidebar or something similar. Other people may not care. Many happily read politically affiliated news knowing that their opinions and actions may be influenced by a media source.