HNHacker News
TopNewBestAskShowJobs

gbro3n

437 karma · joined March 25, 2022

Software engineer working on various platforms, usually around .NET / JS ecosystems, Web Apps, Native, APIs, DBs, things in the middle and bits on the side.
submissionscomments
gbro3n··on [dead]
Every GitHub repository comes with a built-in wiki. It is a separate Git repository that stores markdown files, supports [[wikilinks]] between pages, and can be organised into subdirectories.

AS Notes is compatible with Github Wiki structure. Github wikis can be cloned locally. , Where initialised in the repository root, AS Notes provides wikilink autocompletion, markdown tooling and inline editor formatting (including Mermaid and LaTeX rendering Inline Markdown Editing Mermaid and LaTeX Rendering).

gbro3n··on Do your own writing
I fully agree with the sentiment of the article. I will say that I feel I've had some success in having an LLM outline a document, provided that I then go through and read / edit thoroughly. I think there's even an argument that this a) possibly catches areas you I have forgotten to write about, and b) hooks into my critique mode which feels more motivated than author mode sometimes (I'm slightly ashamed to say). This does come at the cost however of not putting my self in 'researcher' mode, where I go back through the system I'm writing about and follow the threads, reacquainting myself and judging my previous decisions.
gbro3n··on [dead]
21 points, 26 minutes ago. 1 comment. Are posts like these pushed to the top by bots?
gbro3n··on MCP is dead; long live MCP
I have wondered if we're going to end up investing so much in putting up guard rails around AI that we end up with systems of the same complexity as a non AI expert system that runs slower and at higher costs due just having injected models and tokens into the mix! I joke, but it seems like there's a pull towards that.
gbro3n··on MCP is dead; long live MCP
I think we need to just think of agents as people. The same principles around how we authenticate, authorize and revoke permissions to people should apply to agents. We don't leave the server room door open for users to type commands into physical machines for good reason, and so we shouldn't be doing the same with agents, unless fully sandboxed or the blast radius of malign or erroneous action is fully accepted.
gbro3n··on You Need Deterministic Gates for Probabilistic AI Agents
If we want guarantees, (and we do when it comes to security and correct processing of data), we need deterministic gates. The most robust, best specified means of achieving this is MCP, and currently, the best way to manage this in teams is via remote MCP over HTTP.
gbro3n··on MCP is dead; long live MCP
A lot of the best tooling around AI we're seeing is adding deterministic gates that the probabilistic AI agents work with. This is why I'm using MCP over http. I'm happy for the the agent to use it's intelligence and creativity to help me solve problems, but for a range of operations, I want a gate past which actions run with the certainty of normal software functions. NanoClaw sells itself on using deterministic filtering of your WhatsApp messages before the agent gets to see them, and proxies API keys so the agent bever gets them - this is a similar type of deterministic gate that allows for more confidence when working with AI.
gbro3n··on It's time to move your docs in the repo
The code doesn't always say "why".
gbro3n··on It's time to move your docs in the repo
Bit of a plug I suppose, but this was what motivated me to set up AS Notes, my VS code extension which makes VS Code a personal knowledge management system, with linking and markdown tooling. I've built an html converter so they can be published to github pages from the repo. It's here if it's of interest to anyone https://www.appsoftware.com/blog/as-notes-turn-vs-code-into-... ... I'm so much more motivated to write docs when a) its easy to keep them up to date using an agent, and b) someone (agents) will actually read them!
gbro3n··on Show HN: Klaus – OpenClaw on a VM, batteries included
I suspected that might be the case. I'm sure one day soon though there will be a local model as capable as Opus 4.6
gbro3n··on Emacs and Vim in the Age of AI
I will give a go. But my rambling mumblings to Gemini on my phone sor far confirm that I write with more clarity than I speak
gbro3n··on Emacs and Vim in the Age of AI
I didn't get that feeling. But it is long, which is a bit of an AI smell. That said, I think use of AI in writing might not always be a negative. On a couple of documentation pieces I have used AI to provide better structure to writing that I've started and check for technical correctness parts of a document where I need to check my terminology. As long as the original idea is human and AI helps to make the signal clearer, I'm ok with it.
gbro3n··on Emacs and Vim in the Age of AI
I'm a muggle when it comes to vim, but I've considered learning it again recently because of AI. I'm building more than I have in years because I love being able to try things out without investing 3 months to get something working before I can really test the idea. And so I am typing A LOT. Less code, but lots of markdown, prompts and config. My hands are hurting, I really wish I had a power tool for typing. Writing is always going to allow us to be more precise than speech, and is a tool for creative thought in its self. I can see how we might be bearish on our expectations around new adoptees, but I think there's pressure to get more out of our editors too. Two of my recent projects have been vscode extensions, because I'm needing more help from my editor, not less: https://www.appsoftware.com/blog/fixing-agent-llm-context-de..., https://www.appsoftware.com/blog/as-notes-turn-vs-code-into-...
gbro3n··on Show HN: Klaus – OpenClaw on a VM, batteries included
I saw that the Hetzner matrix like has GPU servers < £300 per month (plus set up fee). I haven't tried it but I think if I was getting up to that sort of spend I'd be setting up Ollama on one of those with a larger Qwen3 max model (which I hear is on par with Opus 4.5?? - I haven't been able to try Qwen yet though so that could be b*****ks).
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Can you explain further how that helps / works?
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
For anyone still watching this thread, I have reworked the UI to move the task board to the editor pane from the side bar, and have worked to improve the agents tracking of the core instruction set and current task reference in a way that allows working on parallel threads.

https://github.com/appsoftwareltd/vscode-agent-kanban

gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Yes - and keeps the user in the IDE. There's lots of products with their own harness. I know harnesses are not that complex to build - but VS Copilot has really nice integrations with the editor. Either one of these companies has to build their own editor, the IDE's need to build in their own task management / kanban, or we need an extension (like this one). I'm working on improving the UI task file management and AGENT instruction, but the hooks that VS Code exposes regarding what you can inject into the chat are something I'm having to work around.
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
That does look great. I will check that out. What is the storage for the tasks? I didn't love the Git worktree flow when I tried vibe kanban, spawning lots of folders seemed like it could get problematic on large codebases - unless I'm missing something and just need to get used to that?
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Harsh but fair!
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
I'd been using this workflow for a while, but this post I found on HN a couple of weeks ago really solidified it: https://boristane.com/blog/how-i-use-claude-code/

> The workflow I’m going to describe has one core principle: never let Claude write code until you’ve reviewed and approved a written plan. This separation of planning and execution is the single most important thing I do. It prevents wasted effort, keeps me in control of architecture decisions, and produces significantly better results with minimal token usage than jumping straight to code.

gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Structure certainly helps, and that's what the markdown format here does. How do you measure the effect of the structure?
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Having used a less formalised version of the process (manually managing the agent files but having the user / agent conversation structure the same), I've been getting some really good results out of the agent on some long running complex tasks. I'm seeing so many people talking about leaving agents running and completing projects end to end without any intervention, but my experience so far is that decent software still needs architecture guidance and a human sense of 'taste'.
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Working on additional meta data in the file. What makes you prefer to have lanes managed by file move? I considered it but was concerned about the potential loss of data if there are unsaved changes in the file, or the user accidentally moving a file while the agent is writing to it. I will consider that further though.
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Agreed. Also multiple humans. One task per person works great (no Git conflicts). I'll think about this more. I'm thinking that having the agent work through an MCP server might be a means of mitigating the issue. I'd rather keep the sync process in Git if I can.
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
I would say that a kanban board is not synonymous with scrum. In this workflow, the tasks are a way of organising task threads and recording the consideration, decisions and actions taken while working with an AI agent.
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
That's a nice UI on that board. It's advertising the ability to allow the agent to help manage tasks, where this approach uses the tasks to drive the agent.
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Maybe it will go that way eventually. I haven't got into being able to hand off to agents in the cloud yet, I think as good as LLMs are getting, for complex / professional work the agents still need a lot of steering. I just have to be in the editor with the agent!
gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Intro: https://www.appsoftware.com/blog/introducing-vs-code-agent-k...

Youtube (Quick demo): https://www.youtube.com/watch?v=Y4a3FnFftKw

GitHub: https://github.com/appsoftwareltd/vscode-agent-kanban

gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
I did - GitHub and Trello (and I expect Jira) have APIs that could be used to hook up an MCP server. I liked the idea of conversing with the agent in the ticket, but I decided against that because I'd have to keep refreshing the issues, and it seemed a bit janky moving in and out of the IDE.

I also considered a full harness that could stream / sync the responses, but as per my comment below, implementing a full harness meant loosing a lot of the IDE integration features that come with the hand off to GitHub Copilot.

> I went down the route of implementing a full harness for a while like Vibe Kanban, but the issue was that it was unlikely (without significant effort) to be as good as Github Copilot chat, and it meant forfeiting all of the IDE integrations etc (like diff visualisation for the agents actions etc).

Having worked with a flow similar to this for a while - the markdown files become quite valuable as a history of planning and decisions for features. I didn't want to loose that. I just needed some help with managing the plan files I was maintaining - which the kanban board tooling does. A few command shortcuts via @kanban help too

Regarding what goes into the files, the agent tends to be quite concise - you don't see the whole train of thought that some of the harnesses surface.

gbro3n··on Show HN: VS Code Agent Kanban: Task Management for the AI-Assisted Developer
Thanks. I also saw Vibe Kanban which looked quite mature with lots of features. But I was really liking working with markdown files in VS Code - with everything that comes with that (version control capability etc). I went down the route of implementing a full harness for a while like Vibe Kanban, but the issue was that it was unlikely (without significant effort) to be as good as Github Copilot chat, and it meant forfeiting all of the IDE integrations etc (like diff visualisation for the agents actions etc).

Having the Kanban board in VS Code where I'm working, backed by markdown, GitOps friendly files works really well. Moving from the markdown file to the chat editor to type 'plan', 'implement' isn't what I really wanted, but it's really not a problem once you get used to the flow.

← PreviousPage 3 of 6Next →