TheTaytay

It looks like I'm in the minority after reading this comments, but I'm quite happy to see this announcement.

A "good" standard, free CMS with theming and plugin support without the issues of Wordpress is _welcome_. (And the issues are many: Licensing, trust, drama, security, and cost).

I'm guessing that a lot of cynicism here is coming from this crowd not being the target market of Wordpress in the first place? What were you recommending to non-technical friends and family who wanted a good, open source, affordable CMS to back their website? Wordpress has all the right _ideas_, but the wrong implementation.

I know there is a cooldown period for npm packages, but I’m beginning to want a cooldown for domains too. According to socket, the C2 server is sfrclak[.]com, which was registered in the last 24 hours.

I quite liked this. It feels approachable and to-the-point.

The +1 button doesn’t work?

Devcontainers are looking pretty gold right now…

A lot of automated scanners run during that week.

Yes, I was more impressed with their decoupling of prompts from parameters!

Woah, that community plugin looks so much closer to what I initially thought (hoped) Dspy was!

I think the more likely attack vector in OpenClaw is convincing it to install a malicious npm package or script, have that siphon all machine/env secrets, and then watch those secrets get abused. (Cloud API key -> crypto mining. Wallet key->theft. Npm credentials->worm publishes more copies of itself. GitHub key->more theft and malicious code upload. Email API key->IP theft and password reset on other systems) Almost all of this can be automated, so the attacker doesn’t have to know who you are.

It’s not targeted per se.

I tried it in the past, one time “in earnest.” But when I discovered that none of my actual optimized prompts were extractable, I got cold feet and went a different route. The idea of needing to do fully commit to a framework scares me. The idea of having a computer optimize a prompt as a compilation step makes a lot of sense, but treating the underlying output prompt as an opaque blob doesn’t. Some of my use cases were JUST off of the beaten path that dspy was confusing, which didn’t help. And lastly, I felt like committing to dspy meant that I would be shutting the door on any other framework or tool or prompting approach down the road.

I think I might have just misunderstood how to use it.

Please do elaborate. I’ve only tried switching to codex once or twice, and it’s been probably 3 months since I last tried it, but I was underwhelmed each time. Is it better on novel things in your experience?

I don’t know why this is being downvoted. Danielhanchen is legit, and unsloth was early to the fine-tuning on a budget party.

I’m a huge fan of CLIs over MCP for many things, and I love asking Claude Code to take an API, wrap it in a CLI, and make a skill for me. The ergonomics for the agent and the human are fantastic, and you get all of the nice composability of command line Unix build in.

However, MCPs have some really nice properties that CLIs generally don’t, or that are harder to solve for. Most notably, making API secrets available to the CLI, but not to the agent, is quite tricky. Even in this example, the options are env variables (which are a prompt injection away from dumping), or a credentials file (better, but still very much accessible to the agent if it were asked).

MCPs give you a “standard” way of loading and configuring a set of tools/capabilities into a running MCP server (locally or remotely), outside of the agent’s process tree. This allows you to embed your secrets in the MCP server, via any method you choose, in a way that is difficult or impossible for the agent to dump even if it goes rogue.

My efforts to replicate that secure setup for a CLI have either made things more complicated (using a different user for running CLIs so that you can rely upon Linux file permissions to hide secrets), or start to rhyme with MCP (a memory-resident socket server started before the CLI that the CLI can talk to, much like docker.sock or ssh-agent)

Doltgres actually is a true versioned Postgres under the hood (or MySql).

This sounds really interesting, and I like the ease with which I could spin something up here and get embeddings for sure! But I would think the actual runtime perf of this would be “fine” for some text, but nowhere near Postgres level for all sorts of other stuff, right?

I am a huge fan of Postgres as a database, and of SQL, etc. but I don’t think I understand the benefit of using Postgres’ wire format here since it’s not Postgres behind the scenes. I guess that lets you use psql as the client?

I think this is really neat. You should probably take it as a compliment that the biggest criticisms so far are about the website landing page. ;)

I like canvases in general, and I especially like them for mentally organizing and referring to this sort of broad work. (Honestly, I think zoomable canvases would make a better window manager in general, but I digress)

One small piece of friction: My default mouse-based ways of dragging the canvas around (that work in most canvases like Figma) aren't working. I saw that you had a tutorial, and I have learned to hold space now, but I prefer the "hold middle mouse button to drag my canvas view around".

I've got a couple of research tasks running now, and my current open questions as a very new user are: 1) How easy will it be to store the outputs into a Github repository. 2) How easy will it be to refer back to this later? 3) Can I build upon it manually or automatically? 4) Can I (securely) share it with someone else for them to see and build upon it? 5) Can I do something "locally" with it? Not necessarily the model, but my preferred interface for LLMs at this point is Claude Code. Could I have a Claude Code instance running in one of these boxes somehow? 6) What if I want to do private stuff with it and don't like the traffic going through Spine's servers? Could I pay them for the interface, but bring my own keys? (Related: Can I self host somehow?) 7) When this is done, each artifact it found (screenshot, webpage, etc), is going to be helpful. The data-hoarder in me wants to make sure I can search these later. Heck, if I could do that, this would become my preferred "web browser". (But again, I digress.)

I'm sorry you didn't get more traction here. I've been looking for what you are building. I like your approach (kernel level security, ability to rollback, and phantom credentials!)

Means a lot coming from you - thanks for taking the time to post, and for taking the time to make the Homebrew formula. (I am also a fan of the author's (webcoyote's) other work.)

Is there a better alternative on Mac?

It depends on how much you value the gap between “pretty good” and SOTA… I’ve noticed that Opus is more “expensive”,” but an error-filled rabbit hole is expensive too!

Woah, that looks great. I’ve been looking for something like this. Neither thr readme or the security doc go into detail on the credential handling in the gateway. Is it using tokens to represent the secrets, or is the client just trusting that the connection will be authenticated? I’m trying to figure out how similar this is to something like Fly’s tokenizer proxy.

Yes please! I feel like we need filters for everything: file reading, network ingress egress, etc Starting with simpler filters and then moving up the semantic ones…

I have found that the "advanced voice mode" is dumb as a box of rocks compared to their "basic" TTS version, so I disable it. I've switched to Claude, so I don't know if that's still an option, but if you are tied to ChatGPT, definitely disable it if possible!

I would agree. I don’t use k8s and assumed I couldn’t use this as a result…

I think we are about to see much stronger weight given to accounts created prior to a certain date. This won’t be the only criteria certainly, but it will be one of them, as people struggle to separate signal from noise.

I came away impressed with this article. Whatever he is prompting might have crossed the uncanny valley.

An organization without “tech debt” is not good at prioritizing.

Thank you for writing/publishing this. I especially appreciate the prominent warning at the top not to mistake it for a production library and to suggest an alternative. (It’s surprising to me how often people forget to add disclaimers like that to their code.)

I agree with you, but I don't envy the maintainers. The problem is that it's really hard to tell if someone is skilled like you or just shoveling what an LLM wrote up to the maintainers to have them "figure it out." Honestly, getting a library hard forked and maintained by people that can keep up with the incoming PRs would be a relief to a lot of folks...

Thank you for matchlock! I’ve got Opus 4.6 red teaming it right now. ;)

I think a secure VM is a necessary baseline, and the days of env files with a big bundle of unscoped secrets are a thing of the past, so I like the base features you built in.

I’d love to hear more about the red team breakouts you’ve seen if you have time.

Ugh - yes. I’m seriously close to writing a chrome extension just to warn me or block pages that have that phrase…it’s irrational because there are so many legitimate uses, but they are dead to me.