bloody-crow

I don't think it'd be possible to define fingerprinting narrowly enough to not also outlaw perfectly normal and legitimate usecases.

News flash: you can tell LLMs how to do shit and they're generally pretty good at following instructions.

Those things are good enough to solve novel math problems I've never even heard about, surely it can figure out how you like your commit messages and apply it a million times over in the time it'd take you to make yourself a cup of coffee.

I've never seen a GUI that could do anything git faster than me just doing CLI stuff in my terminal. Not even close.

What do you mean with "manually"?

I type `git rebase -i head~15`, I select the commits I want to include, rearrange lines manually, mark the ones that I want to edit, squash, or reword. I save the buffer, exit, git starts giving me individual commits to edit/reword, so I edit chunks for manually type in the reworded messages etc

These days I just tell LLM what I want and it does git for me as a byproduct and it looks more or less the way I want, except with like 1% typing on my part and 100x times faster.

"Newer cars are much better than older cars". How about this?

It'd be weird to ask for evidence of that statement cause it's very generic and there's like a million instances of newer cars that are shit and old cars that are brilliant. But in general the statement totally holds and you'd need to be insane to be arguing otherwise.

Having 27 years of driving cars experience would add weight to the opinion stated, but otherwise not provide any substantive credible evidence.

I only have 17 years of experience and I fully agree with the author here. This is my personal opinion and I would not be fucked to respond to any demands for evidence since those demands are not meant to be satisfiable in the first place.

This is a subjective statement. What kind of evidence you're expecting here?

Like:

— My new car is much better than my old car — Hurr durr, how can you make those confident statements without showing any evidence, huh?

It's not that deep.

I actually think it's much easier now when most contributions are LLM-assisted or LLM-authored.

Like, at my job we went from wild-west everyone uses their own commit message style to very nice uniformed one now when everyone's using Claude Code following the style enforced by AGENTS.md/CLAUDE.md

I have only about 17 years of experience and I consider myself a moderately advanced git user — I do interactive rebases with squashes, rewords or reordering and I do chunk manipulation per commit all the time. Or at least I used to.

Now I just type into the LLM what I want it do with git and it does it for me, much much quicker. I did not find "babysitting" git painful before, but I today I do feel like doing it manually is a just huge waste of time. A $20 LLM subscription could do this shit for me just as well or better while I spent my time doing more fun and interesting things.

I do know what Sol/Terra/Luna mean, but was also confused for a second on the hierarchy. After doing a bit or research it dawned on me that they are arranged in the order of the sizes of the celestial objects but it somehow wasn't immediately obvious to me from the start.

Anthropic ships models with a helpful one-liner tag that makes the model hierarchy obvious. I think it wouldn't hurt if OpenAI did the same.

But things like taste and quality matter. And I trust the creator of Zig more than the creator of Bun when it comes to said taste.

Having read both articles I'm in the opposite corner. I found Andrew's personal ad-hominem filled emotional post distasteful and Jarred's purely technical and filled with praise of Zig well written and in good taste.

It reads like it's written by a person having a stroke in real time. Really weird formatting, punctuation, structure all over the place. Asinine claims.

I hate the messenger despite loosely agreeing with the message, I guess.

We have a skill that takes a well defined Jira ticket and basically drives it to completion until it produces a human-review ready PR. This process is coded into a bunch of gates that the agent needs to clear before it can advance to the next stage, like fully understanding of the context/problem, fully solidified design (or several), implementation, critic review, submit PR, address CI issues and automated review comments etc.

In practical terms it often means that you can give the agent a ticket and it'll work on it for several hours until the PR is ready. Occasionally it'll run into some question that it needs you to clarify something or make some directional choice, but overall it's pretty autonomous.

Because this takes so long, you normally run 3 or 4 of those in parallel.

Then between shepherding those session, you also run several PR review sessions at the same time. Those also run for quite some time when doing deep investigations.

And then you also have long running discovery/design sessions for various other projects or problems you're working in between.

Right, the secretary would just gossip about it with their friends and partners behind your back.

Work.

I've been using tmux historically and it eventually became too cumbersome since my typical workflow started being a lot more AI-agent heavy. I now run over 10 agents at the same time and they're all working on some multi-hour workstreams that I occasionally need to check in on or unblock. Tmux was not making this particularly easy and I would occasionally lose an agent or forget about it until much later only to realize it's been sitting idle waiting for me to approve something for a few days.

I've tried Cmux, but it didn't do it for me, since the agent statuses were displayed on the workspaces and having multiple agents in the same workspace would sometime produce confusing results.

I've been using Herdr since the start of the week and so far it's been the best in terms of visibility of what my agents are doing and which of them need attention. The only wart I've noticed so far is that the performance is not always great — sometimes I see the text appearing with a noticeable delay as I type it.

Isn't being open source creating incentives for the AI companies to optimize their LLMs for the specific benchmark? I thought all those benchmarks are deliberately closed source primarily for this reason.

But why were they so willing to promote apocalyptic visions in the first place? The answer is money. They pushed the idea that they had a technology that would quickly and utterly transform the economy partly to dazzle Wall Street and secure financing, and partly to scare businesses into rushing into AI adoption for fear of being left behind.

I find a different explanation more plausible. They were actually candid and were saying what they were really thinking at the time. Then later when AI hate emerged and solidified, they were told by their PR advisers to cool it down on doomer perspective and lean more into an optimistic vision.

What kind of privacy are people supposed to expect in a public place like an aquarium?

The benefit of glasses is that you know for sure what they're recording cause they're recording pretty much what you're looking at. A GoPro on your chest could be angled weirdly and you'd have no idea.

Maybe we should also replace traffic signals with a man with a stick directing traffic.

And put a guy on every gas pump in the country so they could pump your gas.

And bring back the telephone network operators that connect you to whoever you want to talk to.

Nah, paying people for work is crazy.

Because this OS developer is also trying to sell you their Music service subscription. I'm sure having this setting would hurt some of their internal KPIs and therefore would never be implemented.

There's a lot of ways a datacenter in your backyard might be less desirable than a corn-field.

Most data center cooling works by evaporation. Hot air or hot water from the servers passes through cooling towers, and water is deliberately evaporated into the atmosphere to carry heat away. That water vapor rises, disperses, and eventually falls as precipitation, but not locally, and not on any useful timescale for the watershed it was drawn from. So the water still exists, but it's been removed from the local hydrological system

Then, there's the ecological angle. Even when companies claim green credentials, locals often scrutinize the actual power mix feeding the facility. If the regional grid is coal or gas-heavy, a data center's carbon footprint can be substantial. There are also concerns about diesel backup generators, potential groundwater contamination, and heat discharge.

Then there's an increased power bills for locals situation, although this one is not as clear and is often disputed. The argument typically goes something like this: utilities operate on cost-recovery models. If a massive new load comes onto the grid and requires infrastructure upgrades like new substations, transmission lines, grid hardening. Those capital costs get socialized across all ratepayers. The data center pays for its energy consumption, but not necessarily for the full cost of the infrastructure built to serve it. That gap gets spread to everyone else's bills.

Because it is not well aligned enough to be able to tell where it's stopped helping you and started fucking you instead.

What if the agent in the middle of helping you runs out of tokens? Would you appreciate if it in the spirit of "exploiting whatever they can to help me" would scan your machine for payment methods, log into your bank account, approve 2FA by reading you mail and plug your credit card into the billing so it could efficiently continuing helping you?

Maybe not the best advice to give to someone who's already has a history of having multiple online personas under different names and getting in trouble for that.

It's very unlikely to cause any real harm — pretty sure any modern harness would ignore and/or flag this output.

I think the intent is that matters more here. The intent is to harm, pretty sure. Poor execution is not an excuse.

I can understand having some moral opposition to using gen-AI or accepting AI contributions to your projects. I personally disagree with this, but it's a defensible position at least.

Trying to harm your users for using gen-AI seems like the worst type of overeager activism that does more to destroy your reputation and trust than achieving anything tangible.

I would advise against hiring the author of this change in any kind of hypothetical scenario where I get a vote based on this behavior alone.

Every time I see those kind of posts, it seems reasonable on the surface. But then you remember than a typical web app might want to do something beyond just serving an HTML template.

Like, what if you want some styling or javascript along with your HTML? Either write everything by hand like it's 2003 again, or start inventing a complex pipeline from scratch in Go. Countless of people have spent thousands of man-hours on solving this problem, but you use Go, so now you do this yourself from scratch.

Or maybe your app needs some relatively complex database access? Writing SQL-spaghetti only gets you so far until you need to do conditional joins and unions and parameterized subqueries etc. God forbid you want migrations too. Go has no answer for this and you either have to hand roll all those things as well, or spend tons of time comparing countless libraries that do some of things you want, but not quite everything, or don't fit into your pipeline for whatever reason.

I'd take an opinionated framework with fat dependency stack that has way more features than I'd ever need over trying to reinvent migrations or CSS preprocessing from scratch in Go, thank you very much.

I big part of the purchase decision making is attributed to the fact that they think they support a real person that is aligned with their ideology.

I'd wager most of them wouldn't have paid money on OnlyFans or purchased the hoodie if they knew the account was AI generated. So it is scam.

Current GraphQL-over-HTTP recommends using 200 OK when returning non-successful properly defined reponses:

- §6.4.1 (application/json): "The server SHOULD use the 200 status code for every response to a well-formed GraphQL-over-HTTP request, independent of any GraphQL request error or GraphQL field error raised."

Ok, but it still seems to me that the messaging you're describing is pretty far from the original commenter's claim of them being "giddy about taking jobs away".

They are giddy about taking jobs away

This is just your interpretation. My interpretation is that they talk about computers being able to perform some intellectual tasks that are now handled by humans in a more efficient and fast manner. They're excited about technological progress and new opportunities it provides, not being "giddy" about unemployment and economic uncertainty.

suck up to Donald Trump

When you're a head of multi-billion dollar company that employ thousands of people and respond to board that expects your company to continue growing and make money for them, it's strategically dumb and irresponsible to NOT suck up to the most childish and vindictive person who has real power to screw over you and all the people you employ who expect you do everything in your power to prevent this.

If you don't do that and Trump fucks your company over as a result, you're just bad at your job as a CEO.