I've been looking for a markdown editor that let's me print the rendered view and have yet to find one. Which is quite surprising given how many there are. I just use my own webapp for now, should probably open source it in case anyone else is looking for this functionality.
If you know of a nice mac app that let's me easily write / view and print markdown I'd love to hear from you!
+1 for Typora. One of the things I like is that it gives you some flexibility in how it handles images you drag into a document for embedding purposes.
My favorite option is the one where it automatically colocates assets by creating a folder with the same name as the file, appends `.assets` to it (<filename>.assets), copies the image there, and then automatically sets up the preview and embed.
Recently adopted https://github.com/marktext/marktext as I wanted the editable preview that Obsidian offers, but for all .md, not just items in my vault. I dig it so far. And it does offer printing of the render.
most of these editors offer pdf exports and the ones that don't they offer html ones that can easily be exported in the browser too. Isn't this enough?
This is something I've been working on exposing to AI labs through my startup LatentEvals[1], and found similar results in other industries from lending to insurance claims.
Happy to share some sample reports if anyone is interested!
Don't have much to add beyond being grateful for everyone working to call this out, with a hope some lawsuits drop and our SCOTUS doesn't decide racial bias in AI is fine because we can't prove the AI is racist in its heart.
There are multiple "sandbox backends"[1] available besides Vercel currently. I'm sure more will follow, and it's open-source so you could always implement your own.
I'm the creator of hty, as part of my work for building custom eval suites at LatentEvals.com I found that AI agents struggled with interactive CLI / TUIs and would resort to setting flags that may be outdated or not exist at all.
I needed a way for AI agents to use all the software that humans do, things like htop, k9s, create-next-app, and even nethack.
How it works: hty wraps any interactive cli in a persistent PTY session. Your agent "sees" the rendered terminal the way you do and types the way you would. I've had a lot of success with agents being able to get through interactive npx setups, play terminal games, and create logical commits from a bunch of work in an long claude code session by using git add -p for interactively patching the git stage.
It's available to use as a simple skill so it works for almost all agents, but you can also use it as the human via the CLI. It's written in zig and built on top of libghostty.
I've been doing bias and misaligned behavior research, creating custom private eval suites to test and compare models. Claude Opus 4.7 is heavily biased and presents clear regulatory and reputational risk.
It seems the initial product footprint tries to sidestep this problem by not giving the agents control on who to lend to or which applications to approve. Even so I think it's quite an optimistic read on their end. Happy to share reports to anyone who's interested (montana@latentevals.com), especially if you work at a frontier model lab and are interested in plugging my evals into your RL systems!
Slightly related, I used Opus 4.6 to help me make marketing copy and ideas for my app. It understood the vibe I was going for on my baby-naming app (elation at discovery, curiosity, shared experiences), while 4.7 instantly wanted to pit the couples against each other (really highlighting the he said/she said) and the marketing copy went from "find a name easier" to "Our new feature is great. You're welcome." I can't get it to drop the snarky sass no matter how much I change CLAUDE.md, brand voice, etc.
All I did was upgrade claude code and use the new model. It most definitely exhibits misaligned behavior (compared to 4.6)
I tried Opus 4.7 for two days before I started beginning every session with "claude --model claude-opus-4-6".
I assume that 4.6 will become unavailable at some point, but I hope not any time soon. 4.7 hit usage limits faster, didn't do anything obviously better, and had more annoying behaviors in other aspects. I don't know if this is strictly a model issue or if there are also problems with how it's harnessed through Claude Code. I'm not willing to spend more time digging into it until I'm forced to.
Nobody is using LLMs to make lending decisions. They are using LLMs to read, extract and audit the supporting documents that go into normal well-tested, compliant and rules-based underwriting systems. And firms A/B test against humans doing the same work. The outcomes your are looking for are metrics like delivering faster results back to customers, with fewer mistakes and less fraud, more compliant, than a comparable human-only process.
Author here, I built this because my agents could not use TUI or interactive CLI software. Think puppeteer for TUIs.
If you've ever asked Claude Code, codex, opencode, etc... to make logical commits from a bunch of changes you might have seen them struggle with moving files around, deleting files when a simple `git add -p` would have let them work through the changes interactivly. ht (the binary name) allows them to spawn their own terminal and drive it similar to puppeteer, sending keys, viewing a snapshot of the terminal and making a decision.
Some other use cases are also solved from CI/CD to making nice demos (it can export images or the format used by asciicast for making videos of the session.
It's powered by libghostty so it has support for all the stuff a modern terminal can do (full color, mouse clicks, etc...) and I've had a lot of fun letting claude run wild and even play games like nethack.
Happy to answer questions, and of course let me know if you run into any issues!
If you know of a nice mac app that let's me easily write / view and print markdown I'd love to hear from you!