OpenCode seemed perfectly workable as a programming assistant. As personal assistants, they all fall short. It's too difficult to really shape their output.
I was briefly impressed with OpenClaw a few times, but ultimately was turned off by not being able to get the models to stop being so damnably verbose. I thought I made progress for a while by having it tweak its soul, iterate, switch models, iterate, switch models, fuse the results, iterate... but ultimately it's all forgotten early in each session. And then one day it killed itself by rebuilding the container it was inside.
Hermes apparently has some plagiarism issues they're trying to cover up [0] and I was deeply unimpressed with their janky, flickery CLI that force-enables a bulky obnoxious header on every launch. Hermes did readily dive into its own source code and did readily confirm that there was no way to disable it. So that's neat. It constantly (wants to) run from upstream master which is unsettling.
Nanoclaw and nanobot seemed fine, but not notably different. There were some common bugs and glitches that caused some minor data loss while configuring nanobot. After that I just deciding to start hacking my own together.
What I really want in a harness is being able to actually control and rewrite the entire context window, like Zed's Text Threads before they obnoxiously and inexplicably removed what, to me, was their most powerful and distinguishing feature.
The timeline here is pretty telling and it looks like Hermes basically points their coding agent at evolver and says "reimplement this yourself." A few days later Hermes magically sports a nearly identical feature.
There's always an excuse, or perhaps someone who actually went through it might be aware of the process and limitations better than your surface level assumptions?
Appreciate the concept, seems deeply useful if a bit underbaked at present.
Active STT allows a "No STT loaded" option that mentions it requires a multimodal LLM like Gemma 4. Except even when I use Gemma 4 features, Ctrl+S to dictate doesn't work. Unless I Voice Edit then quickly Dictate as soon as it processes the silence. Sometimes if the Dictation is triggered on silence, it'll just choose to paste whatever text is on screen. There's no way to dismiss the popup with the text before it's ready to vanish on its own. There's no way to preview what the TTS voices sound like without triggering something to be said manually.
It seems like this will be a great tool soon, but currently there are very many rough edges that would benefit greatly from a nice heavy sanding pass.
Not the same person, but in the event of an AI collapse I think those that relied on it will be at a disadvantage. The rapid deskilling that happens with AI usage is becoming more documented.
Atrophy of your basic skills can still be a problem. Like someone relying on a dozen specialized triangle angle calculators found on Google rather than understanding what SOHCAHTOA is.
It's nearly a line-by-line rephrasing of another story that's linked at the top. In the second half it takes less creative liberties and sticks closer and closer to the original meat-based text.
Most package managers with postinstall scripts are also heavily curated and have reputation systems. As you say, they run as root, so the high trust requirement is definitely warranted. Anyone can upload an npm package.
The operator highlights "Don't stand down" and "Champion free speech" but the thing that grabs my eyes is right at the top, the typo and the heady ego of "programming God!" Everything in the context will guide it afterwards, and I think that right off the bat puts it in a bad position.
This makes no sense given development is not driven by any one entity that might work privately and start publishing later. All development on these projects is done in the open by a variety of entities who have no mutual interest in colluding in this way.
Systemd is a mix of GPL2 and LGPL. Flatpak is LGPL. Neither has a CLA. Many other parts of the ecosystem are GPLs. It makes no sense for this ecosystem to start serving up primarily FOSS applications with FOSS ethos-es as a proprietarified storefront.
So obviously none of this is realistic, even the foundations of it don't align with reality, so what point are you trying to make with this comment? I'm afraid it's going over my head.
AMD is acting like French Aristocracy and they’re telling Linux users to eat cake. It’d be nice if there was digital infrastructure and social will to metaphorically take their heads.
A merge to main itself is pretty substantial, especially a week after saying, "[This] code that does not work. We haven’t committed to rewriting. There’s a very high chance all this code gets thrown out completely."
I was briefly impressed with OpenClaw a few times, but ultimately was turned off by not being able to get the models to stop being so damnably verbose. I thought I made progress for a while by having it tweak its soul, iterate, switch models, iterate, switch models, fuse the results, iterate... but ultimately it's all forgotten early in each session. And then one day it killed itself by rebuilding the container it was inside.
Hermes apparently has some plagiarism issues they're trying to cover up [0] and I was deeply unimpressed with their janky, flickery CLI that force-enables a bulky obnoxious header on every launch. Hermes did readily dive into its own source code and did readily confirm that there was no way to disable it. So that's neat. It constantly (wants to) run from upstream master which is unsettling.
Nanoclaw and nanobot seemed fine, but not notably different. There were some common bugs and glitches that caused some minor data loss while configuring nanobot. After that I just deciding to start hacking my own together.
What I really want in a harness is being able to actually control and rewrite the entire context window, like Zed's Text Threads before they obnoxiously and inexplicably removed what, to me, was their most powerful and distinguishing feature.
[0] https://github.com/NousResearch/hermes-agent/issues/10232
reply