robgough

I just watched a YouTube video from How I AI[1] doing a bit of a preview on Duet. Their point was quite the opposite. The Duet agent is so slow that it's not actually particularly pleasant to use, even if it is smart. I tend to agree, and think speed is a key feature here. If it's not quick, it risks feeling disconnected.

I have, against my better wishes, rather given in to Grokbot over the last couple of weeks. It does feel very nice to use for assistant type tasks. At least part of that is because it feels pretty responsive.

[1]: https://www.youtube.com/watch?v=HYb5w4PfPZM

My first thought after reading this title: Oh cool, they've taken part in a drill and used the motor. I don't really know what that looks like inside a power drill. This will be an interesting post.

Immediately opened it and laughed out loud. Perfect execution, no notes.

This is when I was getting into the industry and I probably held on to UML diagrams as being the one-true-way for far too long ;). Nowadays I'm more than happy with just a post-it note and an arrow.

I do think we lost something in the middle ~20 years there as the industry (understandably) matured. For those of us in tech-forward companies, and industries, everything continued forward... but what I'd certainly missed was how much fear(?) was in the industries that were left behind.

I've been doing some fractional work and I've been getting more and more outreach from organisations that don't have much development knowledge internally and have come to understand the limitations of what they've been building and want expert review. I think there's going to be plenty of work in that, although the bigger question, of course, is how we up-skill people if they're not going through the same learning process that we did.

I think this is a pre-existing problem, as there's quite a lot of people who now have senior in their title but their expertise is very shallow, as they've just been picking tickets up most of their career and have been handed acceptance criteria and requirements on a plate, without really being involved in that part of the process. Obviously not talking about the best of the best here, but the other 90% of working software engineers today.

Inside of organisations, there's still a lot of place for that very human back and forth on what exactly you're building. Navigation of internal politics, org structures etc. What is really exciting for me, is I've never seen so much appetite to actually build ... there's plenty of companies out there for whom that was unthinkable for one reason or another, and now they're hungry for it. Of course it means those companies are going to be learning for the first time the ups and downs of owning your own stack, and there's plenty of opportunity for us there too.

I'm a paid Kagi user (not the API) and one neat feature they have is if you search for something without a question mark, it's just search results. If you stick a question mark on though, it does the quick answer ai response. (this pattern might be common elsewhere, I'm not claiming it's unique)

I've noticed that I'm now getting frustrated if I forget the question mark, as I actively want and prefer an assistant response. I'm sure this wouldn't always be true, but chat is a nice way to do search... and I suspect more thorough than I'd actually be at checking longer-tail sources.

My point is, I think this interface might be what a search engine for humans looks like now.

One of the strengths of Rails was that it helped developers who maybe didn't always know the "best way" to build things to build in a standards compliant way – not that you couldn't do things like return a 200 for Not Found if you really wanted to etc.

I'm always pleased when working with a dev who has Rails experience even if they've since moved stack, as often they have picked up and learned the value of these good behaviours. Perhaps it's as much a community thing as a framework thing, or combination of both.

Agentic development definitely still has room to improve, but I suspect that there is some future framework (maybe even language) designed to help minimise these types of mistakes.

Concerns with his politics aside, I do think there's a truth to what he's talking about here, and that he is just spelling out the reality that developers are, or shortly will be, facing. For many this will be deeply uncomfortable to hear.

It is notable that his perspective in this talk is very much from a developer-user side rather than someone who is responsible for the framework itself. That surprises me, and I suspect it is not a good omen for Rails.

For all of this embrace of agentic development, there is nothing here on how they are adapting the framework for this new agentic development reality. Agents do currently work well with Rails, but there's nothing here pushing things forward as best as I can see.

I know for my own projects I've largely moved to Elixir/Phoenix, for similar reasons to his use of Rust... I didn't want to have to learn it, but now I don't have to and I get to benefit from its strengths.

At the beginning of this year I was fractional CTO at a small b2b startup and was surprised by how what I considered to be the basic requirements of a customer support platform was split across multiple tools and all priced per-user. This essentially forced a small team to limit who in the org had visibility into what was being communicated to customers.

I set out to solve that with https://stayupfront.com and now that the build is in a good place i’m finally having to bite the bullet and learn marketing. I’m also realising that all the advice to start with marketing first was probably good advice!

If you're on one of the betas for about-to-be-released apple OS’s, there's a new describe an extension functionality and building a dark mode for HN is exactly what I just used it to do. Super easy, and synced across all my devices.

I know this sounds like an ad, but I was pretty impressed with it

The only listed feature here I've not got is the automated translation. It will currently draft responses in the incoming language right now – though that's not terribly useful if you don't speak that language.

I'd been considering mostly an English speaking audience at launch. To be more accurate, I was generally thinking about users physically local to me initially, so I could meet with them for customer onboarding and feedback etc.

Your post has got me thinking on an approach to making translation work in an open and honest way, so that is something I will experiment with and hopefully get in quite quickly.

If you'd be interested in helping me test that, please feel free to reach out to [email protected]

I get the temptation to self-host your support platform, as the existing tooling out there can be quite expensive when you want to upgrade from just using an email inbox.

If any founders find themselves reading this, and don't think it's the best idea to self-host your own support infra, I've just spent the last 6+ months building stayupfront.com which has, I think, quite reasonable pricing, and a few more features than this... largely around the customer's portal experience (changelog, roadmap, etc.) and includes monitoring & incident management which I think should all be ran from the same surface.

I've only just soft-launched, so still have founding pricing on there. Would certainly love to speak to others in this space too, as I was surprised how neglected an area it seemed to be when I was trying to find a replacement for jira service desk for a company I was working with at the beginning of this year.

Same here. Over the last two weeks I switched back to Opus 4.8 and turns out that still seems to last the week like it used to. These new models must be eating tokens.

On the other hand, all the little services I'm building for myself are passwordless and use passkeys with emailed codes for setup/reset.

Passwords were a really poor solution to the problem of security, they didn't take the human factor into account. After a rocky start, I'm now finding passkeys super easy and convenient to use. Far more convenient than OTP codes.

I appreciate that if you're OS/browser doesn't integrate nicely with passwords you might be in for a bad time. I'm having a great time with 1Password, though I believe native apple handles them nicely now too – and I suspect this is true of any modern password manager (even the ones built into the browser).

I'm seeing a lot of this across all sorts of apps right now. We're at a sort of cambrian explosion point for software.

I too built my own equivalent of this (belfry.robgough.net). I take it as a good thing, we're all using these tools and coming to similar conclusions.

I suspect over time it'll settle down, once we've gotten comfortable with the new ways of working and found the new normal.

This is great – I built almost the same thing. It's eerie how similar it made that footer on the public websites! Your app definitely looks a bit nicer than mine though! https://belfry.robgough.net

I actually started with a Mac app primarily, as I wanted to have an easier way to switch sessions with the mouse and see Claude Code's status at a glance (I had herdr envy, but wanted to keep tmux). I then figured why not do the iOS/iPad version while I was at it.

Highly encourage you to build out a Desktop version, I'm now using mine as my only terminal and wouldn't go back. Working across machines feels seamless.

obligatory link to https://chatjimmy.ai

I appreciate the kind words. Thank you.

I really wanted to have background audio and make it so the keyboard would directly record audio etc, but my first pass didn't make it through app review (and that was just keeping background audio listening AFTER you'd already started a recording). I could maybe have fought it, but figured if I was already butting up against app review there was little point as they'd likely reject in a future release anyway.

Re: analytics, It is quite weird having no idea how many people are using the app. It does leave you a little blind, but I figure people will get in touch if they have big enough problems with it.

For the Google app, I believe Gemma E2B and E4B both have audio input, so I suspect they're using one of those.

I built my own because I was frustrated with a lot of the free options. Largely because a lot of them had an upsell to be able to do the secondary post-processing step with an LLM. And it wouldn't pick up things like emojis properly or say numbers. Because of that, I left quite a lot of options in there for customising and adding additional steps, etc. Feel free to take a look: dictator.robgough.net

My initial Mac version actually had three additional steps that you could toggle, obviously at the cost of some speed. That is what the website talks about, although nowadays for my own use I've reduced that to just one step and found that it's pretty great. I've got a new version in test to tidy that up, but still lets you define as many steps as you want.

I think that's parakeet doing its job there. That is a closer reflection of what you've actually said. The trick is then throwing that output through some additional deterministic and non-deterministic steps to tidy it up however you prefer. It's exactly what I do with my free and open source dictation app (dictator.robgough.net) for Mac+iOS. And of course, everything stays entirely on-device. Gemma E4B is really wonderful for that second step, it's great at language – but takes up 6-7GB RAM.

It pairs quite nicely with agentic development as it has a history of plenty of open-source projects published on GitHub, which means they have learned to work with Rails et al. rather well.

It also helps to have a "boring" framework with strong opinions and strong community standards etc.

I wouldn't claim it to be the best as I'm not sure how you'd measure that, but I can say that in my experience it is letting me build things to a decent standard really rather quickly.

If you're building something new today, I'd generally recommend starting with a framework that you already know. But for those of us who already know Rails, it continues to be a wonderful choice. I'm playing with Phoenix LiveView for some projects, which is letting me build real-time UI's really easily – but they have some real-time requirements which Rails can do but is not it's strength. For anything a little more CRUD, it's a no-brainer.

Wow, thanks, I'd missed that. It's impossible to keep up with Anthropic and their rather erratic way of operating.

What makes you think your usage is getting cut by 50% post July 13th? It's just that you can use up to 50% of your usage on Fable right now, and that is what is going away.

I'm going to miss Fable too, I found it surprisingly tough going back to Opus when we lost Fable first time round, but paying API costs is simply out of the question for me right now.

Quickly switching between multiple sessions, and seeing which sessions are waiting for input.

I generally run a session per project. Then within each session, a window for Claude, a window for running whatever dev server/logs, a window for neovim, and finally a plain terminal window for things like kicking off deploys etc.

I'm a big tmux fan, but admittedly I've found myself switching between a lot of sessions recently and wishing it was a little bit more mouse friendly.

If you're a Mac user, and can forgive the shameless plug, you might find belfry.robgough.net useful. Connects to local and remote machines entirely through tmux, ssh and libghostty - populating the sidebar from tmux session info, and optionally adds a little Claude visibility in there for good measure.

There's even an iOS/iPadOS version – though for the moment you'll need to build that yourself. Source is all on Github.

I've been surprised by how far my motivation has taken me. I have multiple projects now that are so much further ahead than I have ever managed before. I would get stuck on some small issue or key-decision and then would struggle to move past it.

Certainly, I still have those tendencies, but it's easier than ever to push through and build a throwaway version with code that might not be what I end up shipping, but is enough to help me understand the final shape of the solution. Once that happens, I'm unblocked and away I go again.

The mental cost of building throwaway code has essentially dropped to zero for me. Of course, I keep working now until light mode comes on automatically on my Mac, but that's a whole other problem.

They've said there are limits, and increased limits for those on iCloud+ ... so it seems that Apple is in the selling LLM access game now. I don't think there are any details yet on the nature of those limits, and whether they can be increased as required etc.

Have you seen that they've added an `fm` tool? It was mentioned in the Platforms State of the Union.

Here's what you get when you run it... https://gist.github.com/robgough/7893602895e7580117475076198...

I'm fully expecting an updated foundation model of some kind, but I would bet money they don't utter the words "Google", "Gemini", or "Gemma" even once.

Mac only I'm afraid, but I already did [1]. Packaged it too as I figured it might be useful to others [2] (and I'd want to install it on machine's that I might not have Xcode on)

[1]: https://github.com/robgough/dictator [2]: https://dictator.robgough.net

I spent the best part of a couple weeks making improvements and tidying up the UI, but to actually get something working was essentially only a couple of prompts.

I've got a home-built dictation app that uses a local model to clear up the text and fix grammar. It was super easy to build. I’m extending it to capture meeting notes and summarise too. All on-device.

I saw a little app the other day, I think someone posted on here, that looks at your screenshot and renames the file based off the contents of the file.

There's tons of little examples like that. For a lot of use cases, you really don't need the frontier models.