I am happy that Matrix has found a place in government organizations. For many individual users, Matrix currently solves no problem because they simply can not use it. I hope this will continue to change, I am cheering for you.

Matrix is making real efforts to change this with Matrix 2.0, but still seems to suffer from design debt in many places.

I think this is partially due to the people they attract who largely work on the projects for free: Tinkerers who care about some form of technical elegance for the fun of it. I’ve had a few conversations around FOSS, including Matrix, at this point, and a not-too-uncommon response to my relayed criticisms was “then the user is wrong”.

I can’t tell them what to do. I could tell them what to do if they want adoption by normal people, but many don’t seem to be interested in that and you really can’t argue with that.

If adoption by normal people is a project goal, you have to seriously engineer for that. As much (partially fair) criticism as Gnome gets, they managed to build a desktop package that can seriously be used by normal people in the real world.

I think this is not true anymore. I’ve had it working with while my phone was off.

Users at large (individuals and companies alike) don’t care much about a freedom taken away when a product is a few % better than another, so the biggest player sees if they can get away with it. And once they do it, everyone else does too.

> Most people do not switch their operating system or phone provider every week either. But even if you do not utilize that freedom, it matters because it changes the relationship you have with the provider and the provider has with you.

This is why it’s important to utilize your freedoms. Do NOT let yourself get locked into a particular ecosystem (this is why I’m building a phone app for OpenCode).

This article makes me reconsider using my recently acquired Codex sub in my home setup. I never liked that they hide the reasoning, but somehow overrode the cognitive dissonance because the performance is so good. But the inauditability is already a huge problem.

Incredibly so. All too often a “hey, you shouldn’t have done that here” turns into “NEVER X”, without it actually understanding or making an effort to understand why the correction was made, though I would say usually the context to do so should suffice. I have a rule for it to reason this through and use nuanced language and would say the frontier GPTs (5.4 to 5.6 Sol) get it right around half of the time (very rough estimate). The conclusions are really dumb sometimes.

I’d be interested in an expertly crafted skill here, maybe there are things about it you can still improve. This is an area in which I still find LLMs to be quite lacking.

It also made me appreciate the complexity of the nuances and levels of indirection of what I want to teach it: “Upload to the remote host, which in this case is this but might be another one in another use case, only do this on the local system and this on the remote, do this to X unless Y …, prefer doing Z unless another rule overrides it …”

I sometimes feel like there could be a more expressive way to structure to structure these rules (bring the snark!).

Like yeah, you made it perform better, but I could’ve set any other model to xhigh and spent all the tokens and patience.

It’s surely enough to generate buzz for some headlines about “Fable-level performance”, but I would’ve expected people “in the know” to push back at this more.

It’s an understandable view, but I’d be astonished by any local model processing very long context better than any frontier model (and now many racks are we talking).