22c

Looks like they merged it back in, but it's a shame it was taken out in the first place.

I don't fully get the negativity here. This seems like a middle ground between quick'n'dirty bash script and a well-crafted Ansible playbook.

Half the time if you want to do something quick'n'dirty in Ansible playbooks you need to use shell anyway..

I participated in a hackathon recently where my deployment process was just a bash script doing scp/ssh to a remote server and it feels like Scotty would fit well to that kind of use-case.

Looks similar to sem/weave

https://github.com/ataraxy-labs/sem

https://github.com/ataraxy-labs/weave

Though, despite the claims, I am not sure if these are ready for prime-time yet. I have noticed some rather concerning merge "resolutions".

yt-dlp is running the entire YouTube JS+DOM environment

IIRC they maintain a minimal execution environment that is able to run just the JS needed to pass a few checks but this breaks too often enough that they're planning to make Node.js or another JS interpreter a hard requirement (possibly already happened).

PMs can now also ship their half-baked requirements documents even faster thanks to the help of AI.

I noted something similar a few weeks ago. Companies are finally putting APIs in front of things that should have had APIs for years!

Pretty sure I saw this one a couple of weeks back, or something very similar to it..

https://github.com/philschmid/mcp-cli

Edit: Turns out was https://github.com/steipete/mcporter noted elsewhere in the thread, but mcp-cli looks like a very similar thing.

I believe you're thinking of JScript, they're not quite the same thing.

FWIW I think most users here would prefer you reply to their hand-written comments using your own words, even if you had to use a translator.

An AI agent was used to gain super-user access

No telling if this "hack" wasn't really just prompt engineering followed by hallucinations, particularly if the "hacker" was attempting to exfil data via the agent.

"The key insight is..."

This was either written by Claude or someone who uses Claude too much.

I wish they could be upfront about it.

I can't help but feel there is a funny pattern going on.

A lot of companies want to embrace AI, agents, etc. so they make their platforms easier to use by AI, implementing whatever the latest craze is.

I imagine we're going to see a lot more APIs open up (agentic finances?), a lot of granular access controls, etc.

Where was all of this when regular users had been asking for it for _years_?

Empowering users in general is a good thing, so, in a way, it's a good thing that OpenClaw and things of this nature are exposing all the issues with access controls and API interactions that many of our services have.

Now we just need a reason for AI agents to need "dark mode" on websites...

TIL there's a batch API.. This seems like something a lot of AFK coders should be using.

The pattern for those users is typically they would set some kind of token budget, but their agent would still try to burn through those tokens as quickly as possible, rather than a more sensible "do this at your own leisure over the next ~8 hours".

Looking forward to further commodification of LLM usage in the future to make it more affordable. Batch APIs and more freedom over scheduling/priorities/deadlines seems like the more sustainable approach to driving costs down.

I tried teams, good way to burn all your tokens in a matter of minutes.

It seems that the Claude Code team has not properly taught Claude how to use teams effectively.

One of the biggest problems I saw with it is that Claude assumes team members are like a real worker, where once they finish a task they should immediately be given the next task. What should really happen is once they finish a task they should be terminated and a new agent should be spawned for the next task.

its because people actually want AI to talk to them like that

I can't find the particular article (there's a few blogs and papers pointing out the phenomenon, I can't find the one I enjoyed) but it was along the lines of how in LLMArena a lot of users tend to pick the "confidently incorrect" model over the "boring sounding but correct" model.

The average user probably prefers the sycophantic echo chamber of confirmation bias offered by a lot of large language models.

I can't help but draw parallels to the "You are not immune to propaganda" memes. Turns out most of us are not immune to confirmation bias, either.

Hasn't Michael Burry been talking about this exact thing for at least 6 years now?

Edit:

The Big Short’s Michael Burry Explains Why Index Funds Are Like Subprime CDOs (2019)

https://archive.is/7mOuF

I've thought about building the same thing, by using beads... Glad someone in the hivemind did it.

Gas Town is from the creator of beads.

Sidenote from the article, but TIL Mark Atwood is no longer at Amazon.

What’s old is new again

Let's go back even further.. I get strong nForce vibes from that extract!

Carmack's comments and the comments in the thread entirely surprise me.

256kbit/s was pretty much the standard ADSL speed 20 years ago. I remember thinking it was lucky some of my friends had 512kbit/s and 1500kbit/s was considered extremely fortunate.

Even still calls over Skype worked fine, you could run IRC or MSN Messenger while loading flash games or downloading MP3s. You could definitely play games like Starcraft, Age of Empires, Quake, UT2004, etc. on a 256k ADSL line. Those plans were also about 8x the price of this plan, not even adjusting for inflation.

Not only that, those lines were typically only 64k upload speed. The usefulness of a 500kbit/s up/down line is incredibly high. I think the only reason it might seem less useful now is that web services are not typically optimised to be usable on dial-up speeds like they were 20 years ago.

With the right setup and having feeds/content download asynchronously rather than "on-demand", 500kbit/s is still plenty of internet by today's standards.

Does it mean that they can be stored at room temperature, in humid conditions, etc? ie. requiring no HVAC/dehumidifiers or whatever else might be needed to reliably store archive media?

That's my charitable interpretation.

On the idea of replacing ones self with a shell script, I think there's nothing stopping people (and it should probably be encouraged) with replacing ones use of an LLM with an LLM generated "shell script".

Using an LLM to count how many Rs are in the word strawberry is silly. Using it to write a script to reliably determine how many <LETTER> are in <WORD> is not so silly.

The same goes for many repeated task you'd have an LLM naively perform.

I think that is essentially what the article is getting at, but it's got very little to do with MCP. Perhaps the author has more familiarity with "slop" MCP tools than I do.

There is at least some awareness already when it comes to the performance of the regex engine:

https://github.com/openai/tiktoken/blob/main/src/lib.rs#L95-...

I read the article, I summarised the extremely lengthy points by using AI and then replied to that for the benefit of context.

The HN submission has been editorialised since it was submitted, originally said "Yes, I will judge you for using AI..." and a lot of the replies early on were dismissive based on the title alone.

I think it's a good idea, it does disrupt some of the traditional workflows though.

If you use AI as tab-complete but it's what you would've done anyway, should you flag it? I don't know, plenty to think about when it comes to what the right amount of disclosure is.

I certainly wish that with our company, people could flag (particularly) large commits as coming from a tool rather than a person, but I guess the idea is that the person is still responsible for whatever the tool generates.

The problem is that it's incredibly enticing for over-worked engineers to have AI do large (ie. diffs) but boring tasks that they'd typically get very little recognition for (eg. ESLint migrations).

Hmm kinda makes sense to keep them separate because the agents perform differently, right?

You might want to tell Claude not to write so many comments but you might want to tell Gemini not to reach for Kotlin so much, or something.

A unified approach might be nice, but using the same prompt for all of the LLM "coding tools" is probably not going to be as nice as having prompts tailored for each specific tool.

The entire article, probably quite intentionally, seems to overuse semicolons (in my opinion). I say this as a semicolon enjoyer, but I think the overuse of semicolons in this article leads the reader to a bit of semicolon fatigue by the end of it.

Someone better versed with parsing crab-grade enterprise-ready Rust could probably give more insight but I think it boils down to a lot of

    assert 1 != 0;

Part-way through the section on bit-twiddling, I thought to myself "Oh I wonder if we could use a solver here". Lo and behold, I was pleasantly surprised to see the author then take that exact approach. Love the attention to detail in this post!

French door has less insulation because there's more "seams". Also typical french doors tend to have an ice machine or water dispenser, which is even less insulation and/or more seams.