1 - I have a $200 Claude and a $100 Codex ($200 of that is paid for by my job)
2 - I generally run everything through openrouter. I've tried local models, but with subscription pricing it doesn't make sense for me to use local most of the time - though I do use local specialty models for Whisper and Chatterbox
3 - If I'm using Codex or Claude directly, I'm using the desktop apps. The apps are MUCH more useful than doing everything on the command line now.
But mainly, I'm switching to my own harnesses via my own agent factory.
4 - My own, called Workforce, which include general agent tasks + a lot of focus around code agents. (Workforce has agents that build and deploy Workforce, for example.). It also provides containers to agents for some bit of containment.
5 - My own... the same Workforce.
My main use cases are code and running a personal assistant I'm building called Clara. Its very similar to what a Hermes would do, but its all built exactly the way I want.
And that's my advice to everyone - don't use off the shelf agents and try to understand how they work - build your own and make them work how YOU want. There is nothing magical about OpenClaw and Hermes, and you can bootstrap one pretty quickly with Opus 5.5 now...
Edit: I should probably have said, my use case is software development - we're a consultancy that builds mainly back-office systems for customers - so I'm "coding" or having agents code 8-10 hours a day, and then my own projects after work. I just about make it under the $200 Claude plan limits though as I add more and more agents, that's going to get uncomfortable.
Curating your feed also works on BlueSky. Sure there are anti AI people there, but the crazy ones I just block. It’s really not that hard. And I know there’s no algo behind what I’m seeing.
I do admit that there is some FOMO, but that’s what HN is for, to surface that stuff so I don’t have to go read it on X.
I choose Bsky because I’m not giving eyeballs and money to an evil toddler. I’m already doing enough of that with my 401k and taxes.
You can certainly use both X/Twitter and BlueSky (and Mastodon, for that matter), and I did for a while.
Just if you curate your Twitter feed, you gain very little extra from BlueSky or Mastodon, and if you choose only the latter two, you get a much more biased and limited set of views. (Twitter has plenty of crazies from all parts of the political spectrum, but BlueSky and Mastodon run mostly left, and have much, much smaller user bases). HN also is extremely limited in what it discusses, so it doesn't make up for what is missed by ignoring X either, IMO. X is still one of the most efficient general public squares by a long shot.
If you can't stand Elon and don't care about what you're missing on X though, I can fully understand just not bothering with it. You aren't missing much.
Also, we don’t know how many billions of dollars was spent on making it work. They are running 1000s of agents against their codebase 24/7, and still only producing what they’ve put out so far.
It might be fully automated and eventually the agents figure out all of the bugs, but I suspect the costs are so large that no sane company would ever write code this way, and probably WAAAY more expensive than just hiring humans to write and test it.
Myself and a couple friends bought this device a few weeks ago and with the firmware being released, its an amazing device.
I love the idea of cheaper Chinese music hardware with the ability for open source firmware and apps to be loaded into them. I hope the success of this sees a sampler from M-Wave - I'd love a Chinese 404 or MPC...
M-VAVE should pay attention and make an updated FM1-style machine that allows firmware switching from USB storage - the current method is via MIDI Sysex only (USB MIDI class device) - but if they do an upgrade to this hardware, it could be quite possible to just switch firmwares dynamically this way.
And, in so doing, this little Chinese company will snatch the revolutionary glory from a lot of incumbents who have very specifically attempted to not do this kind of music technology instrument for decades. (I'm looking at you, Yamaha, who have had prototypes of this sort of things on the bench for decades but always decided 'not to destroy the existing player keyboard market', instead!)
I am so ready for the world where a $60 device not only provides amazing real-instrumentation haptic experience, but also competes solidly with the iOS-music-making app+controller segment, the laptop-on-stage-plugin-host thing, and all the other rigid directions the music tech world has been enforcing on us ..
This is why I spent a lot of time building a design system first, that I can then re-use in my projects. My system is built out of properly CSS tokenized and organized Vue components, and the agent has instructions that it cannot create HTML that isn't made of components - and that if it needs a different UX (which I will have designed with it), then it needs to be built as a component.
What's nice is that you can then write linters for rando CSS and component violations most of the time.
Even then, you sometimes still have to beat it down when it goes rogue - but it does tend to bring my daily frustration down a bit. (Along with a process during design to preview these layouts before they get to a coding agent.)
And once you have a design system that suits your needs, its easy to add in as skills/scripts to any new project. I keep a github repo with all of these bits and bobs, with an agents.md that teaches the agent how to use the repo.
But in short: if the LLM keeps screwing it up, build tools and define it once - stop trying to prompt your way out of it every time.
Someone ripping a copy of The Odyssey for watching in their own home is a loss of profit for the company's lawyers, and must be punished to the fullest extent of the law.
A company ripping off all of humanity to create profit for their company's lawyers is perfectly fine.
There's nothing magic here. Its money deciding the rules. Like it always has.
If all you’re doing is writing then it’s not worth it, but for me the iPad is a fantastic piece of kit that can consume media, create media, and of all types, writing to fully mastered music albums.
Most people I know that make music on an iPad only use it for specific plugins or MIDI apps. They bounce the stems out to WAV and then mix/master it in a full desktop DAW.
You'd go through a lot of unnecessary suffering trying to do a professional mixdown and master on iPad.
A musician friend used to actually do recording with garageband on an iPad. I use mine for sheet music a lot and even sprang for the external foot pedal for page turns. There was one rehearsal where I didn’t have a chance to scan everything in advance and was playing from printed music for one song and I kept stepping on the pedal to turn the page and nothing happened.
I’ve not done it, but it seems it could be a good alternative to a laptop for digital synth stuff.
- AI isn't bound by need for rest, vacations, sick days, or labor laws
- AI doesn't bounce from company to company, taking your business knowledge with it (actually this isn't technically true based on the practices of AI companies, but that's not a technical requirement)
- AI doesn't join a union and stop work in demand for higher pay or workers rights
This is what CEOS and capitalists are thinking. For capital, the best outcome is to not have any labor at all. And if you can do that when your competitors can't, then you have a huge market advantage. (Slop notwithstanding)
I'm not saying this is a "good thing" but this is what drives the market. Less labor revenue in the long term and money printing machines.
The issue is, of course, that the quality of work is not good, and this will eventually show itself, likely in the total collapse of the US economy, but until then I wish them good luck with this.
2 - I generally run everything through openrouter. I've tried local models, but with subscription pricing it doesn't make sense for me to use local most of the time - though I do use local specialty models for Whisper and Chatterbox
3 - If I'm using Codex or Claude directly, I'm using the desktop apps. The apps are MUCH more useful than doing everything on the command line now.
But mainly, I'm switching to my own harnesses via my own agent factory.
4 - My own, called Workforce, which include general agent tasks + a lot of focus around code agents. (Workforce has agents that build and deploy Workforce, for example.). It also provides containers to agents for some bit of containment.
5 - My own... the same Workforce.
My main use cases are code and running a personal assistant I'm building called Clara. Its very similar to what a Hermes would do, but its all built exactly the way I want.
And that's my advice to everyone - don't use off the shelf agents and try to understand how they work - build your own and make them work how YOU want. There is nothing magical about OpenClaw and Hermes, and you can bootstrap one pretty quickly with Opus 5.5 now...
Edit: I should probably have said, my use case is software development - we're a consultancy that builds mainly back-office systems for customers - so I'm "coding" or having agents code 8-10 hours a day, and then my own projects after work. I just about make it under the $200 Claude plan limits though as I add more and more agents, that's going to get uncomfortable.
reply