Definitely appreciate this. I already have Typora which is commercial but fantastic product so I don't really need another viewer but others for sure will.

Glad you used Tauri to make this. I will check it out.

I tend to use 'bat' or 'glow' though I've tried 'mdlook' and 'mdcat' as well.

I live in my terminal but for some reason any TUI markdown viewers just don’t do it for me

Yeah - I've tried a bunch of them, and nothing's really perfect but those seem to be good enough for lightweight use.

Oh nice! I’ve never checked out Typora before I’ll take a look as well

Can +1 Typora, it's quite excellent.

I think they are using Claude to come up with these and they will bringing one every second day... In fact, this is probably routine they set.

Honestly, you shouldn't be working on a plane. This thing where people are plugged in all the time is just insane.

Yes, you lost some abilities. Install local model so you have someone to talk to while you are on the plane ;)

I don't use Claude so this doesn't affect me, but I worry it will spoil the fun for me for following reason.

They inflated how much their tools burn tokens from day one pretty much,remember all the stupid research and reports Claude always wanted to do, no matter what you asked it. Other tools are much smarter so this is not such a big deal.

More importantly, these moves tend to reverberate in the industry, so I expect others will clamp down on usage a lot and this will spoil my joy of using AI without countring every token.

Burning tokens doesn't just wastes your allotment, it also wastes your time. This gave rise to turbo offering where you get responses faster but burn 2x your tokens.

Elm is a language I enjoyed the most. I love Ruby, I loved some other languages, even Haskell I enjoyed, but Elm is special. So let's make this work.

Now that you got foundation created, let's see how to move it forward.

I've been using OpenCode and Codex and was just fine. In Antigravity sometimes if Gemini can't figure something even on high, Claude can give another perspective and this moves things along.

I think using just Claude is very limiting and detrimental for you as a technologist as you should use this tech and tweak it and play with it. They want to be like Apple, shut up and give us your money.

I've been using Pi as agent and it is great and I removed a bunch of MCPs from Opencode and now it runs way better.

Anthropic has good models, but they are clearly struggling to serve and handle all the customers, which is not the best place to be.

I think as a technologist, I would love a client with huge codebase. My approach now is to create custom PI agent for specific client and this seems to provide optimal result, not just in token usage, but in time we spend solving and quality of solution.

Get another engine as a backup, you will be more happy.

1 client, 1 agent? Interesting

A developer using Claude Code found this bug. Claude is a tool. It is used by developers. It should not sign commits. Neovim never tried to sign commits with me, nor Zed.

They are running out of things to ban...

Did they not just launch yesterday and they are already half way there? Am I wrong?

They are right now only 44000km not 170000km, it's ai hallucinated slop (unless... NASA app is also ai slop...)

Absolutely agree, but as technologists our instict is to solve problem as technical, not as social.

Is it the "when all you have is a hammer..." issue?