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 A Claude Code and Codex Skill for Deliberate Skill Development
I think just keeping an ear to the ground, and sometimes through querying LLMs themselves about how to solve certain problems. Most vendors seem to follow Anthropics lead on configuration and agent instruction (though it certainly varies). I just picked up this link from HN today which was good https://claude.com/blog/how-claude-code-works-in-large-codeb... - I haven't been using hooks until now which the article emphasised, but I can see how they would be useful (for example for running formatters to enforce file format rules / clean up after the agents).
gbro3n··on A Claude Code and Codex Skill for Deliberate Skill Development
I'm still finding skill use to be far less reliable than clear instruction in AGENTS.md - I appreciate the idea is to give the agent the opportunity not to add the skill if not relevant to avoid context bloat, but there's no way (without an explicit instruction in AGENTS.md) to ensure that the agent will use the skill, and that point they might as well be any markdown file referenced at any location.

While building https://www.agentkanban.io (a Github CoPilot integrated task board), I experimented a lot with instruction placement. A single degree of separation from AGENTS.md works really well (I needed a robust means of having the agent pick up task specific IDs and so settled on a file called INSTRUCTION.md in a file managed by the tool which avoids polluting AGENTS.md as much as possible). I experimented with skills, but they were skipped too often for the tool to work as reliably as it now does.

gbro3n··on If AI writes your code, why use Python?
The larger models really are more reliable at following instruction and reasoning their way to solutions. I haven't found that the harness makes that much difference. CoPilot, Claude, Pi, all see similar results for me. What really does make a difference is clean task separation and a clear plan / todo / implement workflow. I've consolidated a lot of the way I work with agents in https://www.agentkanban.io - the task board keeps the tasks discrete and minimal. I built in plan todo implement into the agent instruction that binds the board task to the chat.
gbro3n··on Googlebook
Although there's a lot of consumer tools that won't stick, because they just don't actually help, AI is going to make big inroads for lots of different categories of task (just not all). It seems software engineering (or the act of coding specifically) is going to be heavily affected, because a lot of the labs focus is going into developing AI coding skills, and because it's easier to verify correctness than it is in many other problem domains. I've moved my focus to retooling - consolidating much of my workflow in a tool I'm working on https://www.agentkanban.io - A remote kanban board with agent harness integration (Github CoPilot currently) and context management. It's a tool that I use everyday in my own agentic coding workflows, and I can honestly say that it improves the quality of the code produced and reduces friction in organising working on concurrent features.
gbro3n··on Software engineering may no longer be a lifetime career
I think it's going to be a shift in skill set, like the constant change that has gone before. I've always primarily considered by self an application developer, but of late I've become more software architect, more devops, more tester. Software engineering skills always leaked into these domains before AI, I think it's just a shift in the time spent there now we're not manually writing so much code. And shipping is STILL hard. I've moved my focus to retooling - consolidating much of my workflow in a tool I'm working on https://www.agentkanban.io - A remote kanban board with agent harness integration (Github CoPilot currently) and context management.
gbro3n··on Incident with Actions – Resolved
Legendary comment. Thank you for your insight, wit and for taking the time to contribute.
gbro3n··on Incident with Actions – Resolved
This is the effect of agentic workflows. I know how much faster I've been going since the agents got good. I'm not surprised they're struggling.
gbro3n··on Windows quality update: Progress we've made since March
I discovered NixOS this year and I'm afraid I won't be back Windows. TBH Windows has been pretty good to me. This laptop was running at least 4 years on the same install. I never really found that Windows got in my way except for "This file is being used by another process" annoyances that I don't get with Linux. For ages I felt that Windows + WSL2 was the best of both worlds, but NixOS gives me a reproducible OS configuration that means I'll never have to fully build my OS again, and every installed app / routine is documented in code. This feels like the way forward.
gbro3n··on Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
I guess we will need to wait and see if AI can remove ALL of the complexity that requires a software engineer over a business analyst. I can't currently believe that it will. BA's I've worked with vary in technical capability from 'having coded before and understanding DB schema basics and network architecture' to 'I know how the business works but nothing about computers'. If we got to the point in the future where every computer system ran on the same frameworks in the same way, and AI understood it perfectly, then maybe. But while AI is a probabilistic technology manipulating deterministic systems, we will always need people to understand whats going on, and whether they write a lot of code or not, they will be engineers, not analysts. Whether it's more or less of those people, we will see.
gbro3n··on Opus 4.7 to 4.6 Inflation is ~45%
Do you think if you or me stopped using AI that everyone else will too? We're still what we always were - problem solvers who have gained the ability to learn and understand systems better that the general population, communicate clearly (to humans and now AIs). Unfortunately our knowledge of language APIs and syntax has diminished in value, but we have so many more skills that will be just as valuable as ever. As the amount of software grows, so will the need for people who know how to manage the complexity that comes with it.
gbro3n··on Opus 4.7 to 4.6 Inflation is ~45%
I feel like I'm going to have to try the next model. For a few cycles yet. My opinion is that Opus 4.7 is performing worse for my current work flow, but 4.6 was a significant step up, and I'd be getting worse results and shipping slower if I'd stuck with 4.5. The providers are always going to swear that the latest is the greatest. Demis Hassabis recently said in an interview that he thinks the better funded projects will continue to find significant gains through advanced techniques, but that open source models figure out what was changed after about 6 months or so. We'll see I guess. Don't get me wrong, I'd love to settle down with one model and I'd love it to be something I could self host for free.
gbro3n··on Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
I completely see your point, but when my / developer time is worth what it is compared to the cost of a frontier model subscription, I'm wary of choosing anything but the best model I can. I would love to be able to say I have X technique for compensating for the model shortfall, but my experience so far has been that bigger, later models out perform older, smaller ones. I genuinely hope this changes through. I understand the investment that it has taken to get us to this point, but intelligence doesn't seem like it's something that should be gated.
gbro3n··on Migrating from DigitalOcean to Hetzner
I did the same this year. I really liked Digital Ocean though, compared to more complex cloud offerings like AWS. AWS feels like spending more for the same complexity. At least DO feels like it does save time and mental band width. Still though, the performance of cloud VPS is abysmal for the price. I'm now on Hetzner + K3's plus Flux CD (with Cloudflare for file storage (R2) and caching. I run postgres on the same machine with frequent dump backups. If I ever need realtime read replicas, I'll likely just migrate the DB to Neon or something and keep Hetzner with snapshots for running app containers.
gbro3n··on Claude Code Routines
I have heard it said that tokens will become commodities. I like being able to switch between Open AI and Anthropics models, but I feel I'd manage if one of them disappeared. I'd probably even get by with Gemini. I don't want to lock in to any one provider any more than I want to lock in to my energy provider. I might pay 2x for a better model, but no more, and I can see that not being the case for much longer.
gbro3n··on Write less code, be more responsible
My current take is that AI is helping me experiment much faster. I can get less involved with the parts of an application that matter less and focus more (manually) on the parts that do. I agree with a lot of the sentiment here - even with the best intentions of reviewing every line of AI code, when it works well and I'm working fast on low stakes functionality, that sometimes doesn't happen. This can be offset however by using AI efficiencies to maintain better test coverage than I would by hand (unit and e2e), having documentation updated with assistance and having diagrams maintained to help me review. There are still some annoyances, when the AI struggles with seemingly simple issues, but I think that we all have to admit that programming was difficult, and quality issues existed before AI.
gbro3n··on The End of Eleventy
I built static site publishing into AS Notes, to add in to the mix (https://www.asnotes.io an extension for VS Code). It's markdown and wikilink based, and can publish either the whole workspace or from one or more specific folders. I've designed it so that I was not dependent on any platform for my static sites. Publishing is a pro feature, but it's a one time lifetime licence purchase.
gbro3n··on OpenClaw’s memory is unreliable, and you don’t know when it will break
What sort of tasks do you have it do for you?
gbro3n··on OpenClaw’s memory is unreliable, and you don’t know when it will break
That would be great if that comes to fruition. Investing in a model with weights updates would be like investing in employee training, rather than just giving the same unreliable employee more and more specific instructions.
gbro3n··on OpenClaw’s memory is unreliable, and you don’t know when it will break
I've used open claw (just for learning, I agree with the author it's not reliable enough to do anything useful) but also have a similar daily summary routine which is a basic gemini api call to a personal mcp server that has access to my email, calendar etc. The latter is so much more reliable. Open claw flows sometimes nail it, and then the next day fails miserably. It seems like we need a way to 'bank' the correct behaviours - like 'do it like you did it on Monday'. I feel that for any high percentage reliability, we will end up moving towards using LLMs as glue with as much of the actual work as possible being handed off to MCP or persisted routine code. The best use case for LLMs currently is writing code, because once it's written, tested and committed, it's useful for the long term. If we had to generate the same code on the fly for every run, there's no way it would ever work reliably. If we extrapolate that idea, I think it helps to see what we can and can't expect from AI.
gbro3n··on OpenClaw’s memory is unreliable, and you don’t know when it will break
I've had a crack at this problem in Agent Kanban for VS Code (https://github.com/appsoftwareltd/vscode-agent-kanban). The core idea is that you converse with the agent in a markdown task file in a plan, todo, implement flow, and that I have found works really well for long running complex tasks, and I use this tool every day. But after a while, the agent just forgets to converse in the task file. The only way to get it to (mostly) reliably converse in the task file is to reference the task file and instructions in AGENTS.md. There is support for git work trees and skipping commits of the agents file so as not to pollute the file with the specific task info. There is also an option for working without work trees, but in this flow I had to add chat participant "refresh" commands to help the agent keep it's instructions fresh in context. It's a problem that I believe will slowly get better as better agents appear, and get cheaper to use, because general LLM capability is the key differentiator at the moment.
gbro3n··on A practical guide for setting up Zettelkasten method in Obsidian
I built the AS Notes extension for VS Code (https://asnotes.io) partly because I wanted to be able to write my notes with the support of other VS Code extensions, and because of the agent harness options in VS Code (copilot etc). The key thing for easy zettlekasten management is really good wikilink support in markdown. AS Notes supports nested wikilinking and automatic updating in the index on rename etc.
gbro3n··on The threat is comfortable drift toward not understanding what you're doing
That is a very possible reality. Pay extra for no ads or a reduced cost trip if you consent to having your eyeballs held open while separate ads are played to each eyeball.
gbro3n··on Show HN: I made a YouTube search form with advanced filters
Maybe, I'm not clear what the goal is though.
gbro3n··on Show HN: Modo – I built an open-source alternative to Kiro, Cursor, and Windsurf
This looks great. Building right into the editor looks like a solid way to go. I built "Agent Kanban" (anextension) for VS Code to enforce a similar "plan, tasks, implement" flow as you describe. That flow is really powerful for getting solid Agentic coding results. My tool went the route of encouraging the model via augmenting AGENTS.md and having the Kanban task file be markdown that the user and agent converse in (with some support for git worktrees which helps when running multiple sessions in parallel): https://www.appsoftware.com/blog/introducing-vs-code-agent-k...
gbro3n··on Show HN: I made a YouTube search form with advanced filters
It's always surprised me that Youtube being owned by the worlds leading search company has such awful on-site search. I've always left Youtube and searched for youtube videos via Google search, which brings up better results!
gbro3n··on The threat is comfortable drift toward not understanding what you're doing
I think a good analogy is people not being able to work on modern cars because they are too complex or require specialised tools. True I can still go places with my car, but when it goes wrong I'm less likely to be able to resolve the problem without (paid for) specialised help.
gbro3n··on LLM Wiki – example of an "idea file"
I built AS Notes for VS Code (https://www.asnotes.io) with the option for this usage pattern in mind. By augmenting VS Code so it has the tooling we use in personal knowledge management systems, it makes it easy to write, link and update markdown / wikilinked notes manually (with mermaid / LaTeX rendering capability also) - but by using VS Code we have easy access to an Agent harness that we can direct to work on, or use our notes as context. Others have pointed out that context bloat is an issue, but no more so than when you use the copilot harness (or any other) inside a large codebase. I find I get more value from my AI conversations when I persist the outputs in markdown like this.
gbro3n··on The CMS is dead, long live the CMS
I agree. Now we have the ability to have agents reason over our notes, it's more important for them to be in plain text. It was a big part of the reason I developed the AS Notes extension for managing documentation and blogs in VS Code / Markdown (https://www.asnotes.io)
gbro3n··on Why are we still using Markdown?
Because we need to get information down quickly, but still have the option of parsing to a presentable format. Markdown is not perfect, but it's far better for the efficient capture of information or document authoring. I recently built AS Notes for VS Code (https://www.asnotes.io). It's markdown based, with wikilinks, mermaid diagrams, with the ability to publish to github pages etc. There is no way I'm writing my day to day notes with HTML and anchor tags without it being a huge distraction. And HTML is so much harder to read in longform if you need to come back end edit your writing. Markdown is for humans where HTML was designed to be simple, but is ultimately for parsers.
gbro3n··on The Windows equivalents of the most used Linux commands
Really? That's awesome
← PreviousPage 2 of 6Next →