I miss the days when the SEO bots weren’t winning.

The ruling is flawed, searching the Internet has been an “AI” battle for 20 years using the predecessors of LLMs to sort out “what people really want” vs the websites that are precision honed to receive as many top-ranking search result returns as possible. Then, of course, Google forgot the n’t in “At least don’t be Evil.” and they started pushing promoted (aka paying customers’) results higher in the rankings.

If you simply unplug Gemini, what replaces it? Is Hadoop “too smart” for the ruling? Multiple cross references of content and links and what all else proprietary algorithms the Google goblins cooked up over the last 20 years, at what point is that AI/not AI? If Gemini gets repackaged as “totally not AI tech” - does that make it now legal?

People do need to curb their enthusiasm, on both sides of the AI questions. It’s a tool, it’s not perfect for everything, it is good for some things, better than the best of what came before - for some things.

remind yourself of things you already know (what was the command for X again)

Speak for yourself, they remind me of things I used to know. I have reached a point where I feel like I have forgotten more than most people know.

This isn’t new since ChatGPT and friends dropped. For years before that, Google search results did limited interpretation of natural language requests, not just keyword match frequency. The SEO arms race drove a different kind of AI in search fetching for at least a decade before natural language chatbot tech hit the scene.

I don’t know how much is intentional enshittification to make AI results look better vs how much is simple neglect of the SEO arms race vs maybe it’s genuinely getting harder to deliver good simple search results with LLMs acting as SEO agents?

What I do know is: “AI Mode” delivers more useful information than the old style page link list does these days. The pages linked from the AI Mode results tend to be relevant and useful more than the top page of page links. Hallucinations are way down from where they were 2+ years ago, even better than “top results” misses used to be, IMO. If you’re not getting enough sources in your first AI mode response, ask for more - it delivers.

As was true since the first days of the internet: trust nothing. This is random junk people stick on the web for their own purposes, you have been warned.

US, UK, tale as old as time really - how to stay powerful? Undermine your competition.

Again. They’re on the rinse-lather-repeat cycle for 400 years now.

Google quotes a standard Gemini query at 0.24Wh - and I’ll say if you’re continuously asking normal questions and getting answers at normal speed from Gemini, you might get 100 queries in per hour - so, at that rate, Gemini is consuming 24 watts while in use.

Interestingly, the human brain also consumes about 20 watts, so I’m here wondering if Gemini is cooking its own numbers on the first response.

When you ask it complex questions, it takes longer to respond, but says they might range up to 15Wh per response, so maybe more on the order of 500W while in continuous use for complex queries - like the power of 25 human brains instead of one.

Of course, human watts come from direct digestion of rice and beans and other “solar powered” energy sources, while electricity comes from more environmentally challenging sources.

whether it’s worth the effort to do a thorough review.

If the vibe coder learns how to vibe better…

I’ve been using LLMs for a lot of things since last October, the models have improved pretty dramatically since then, but so have my skills in using them - so it’s hard to tell (and probably unimportant) which factor is more important in the increased quality and efficiency of my code production and reviews over the last year.

Using LLMs to review code (regardless of who/what wrote it) is a more efficient way to improving code quality, security, maintainability, etc. than just reading it all yourself. Certainly don’t go blindly trusting the LLM reviews, but if you haven’t tried them for pull request review, you should…

If you’re going to TOR and discard all tracking cookies, and only use anonymized contact methods (not e-mail accounts linked to your credit cards…) then you’re on the right track.

Wrong yourself. Strong secure identification would be required in places that require identification. Users and useees would make a conscious choice when they are going to act anonymously or allow anonymous participants.

Already 99% of the web effectively identifies users well enough for law enforcement to track them down, this would just bring that process into the light, and when you want anonymity you would take necessary steps to make it true, instead of a false security blanket like all the BTC idiots talked like they had before (and even after) Dredd Pirate Roberts got taken down.

The problem with closed meshnets is: scale. Do you have “critical mass” necessary to keep people engaged and returning and creating new content?

We’ve been rolling along with weak IDs on the internet since the beginning. Strong, secure identification would change the nature of most of these problems. It would make anonymity a choice instead of an illusion, you want to be anonymous, you have to work at it. As things are, people think they’re anonymous, but they really aren’t - and yet most services treat people as if they are anonymous so people tend to act that way.

The value of any given contribution is the same, regardless of whether the code was written by a seasoned developer, a neophyte as a first project, an LLM, a team of high school students learning the language, or space aliens - the code is the code, it helps or hurts exactly the same when merged with zero connection to who or what wrote it.

Caring about who or what wrote the code is applying prejudice. Prejudice works well in a lot of cases, but it’s no guarantee.

If you are accepting submissions from anonymous, or insecurely identified (same thing, really), contributors, they should all be treated with zero prejudice. You might think you know who or what wrote the code based on the name in the linked e-mail address, the way comments are (or aren’t) written, or a million other “tells” in the code that aren’t about the function of the code - that’s really irrlelevant. What’s relevant is: what does the code actually do after it’s merged.

If you’re trusting code because you think its “tells” track with seasoned developers, be prepared - very very soon - for maliciously crafted code full of “seasoned developer” tells to slip in backdoors and other malware, because bad actors are already using AI to mimic the things you want to see in a submission in order to gain your trust and lower your guard against them slipping in the things they want in your code base.

For this, we need to start using (much more) secure ID tech, so you really know who is submitting, and prioritize those who have made good quality submissions in the past. Sadly, this may negelect “unknown” authors, but such is life.

Also, we may need to recruit more code authors / wanna be code authors to act as code reviewers more of the time, perhaps following the model we use in our commercial operation where all authors also act as reviewers.

So… if using office space for data centers, they just need to lower the server density until it’s compatible with the unused office space’s capacity… like our old unused K-Marts and grocery stores become halloween haunted houses…

We only do about 3-10 reviews a week, depending… it’s not there to replace you, it’s there to help.

Before AI assistance we would do fewer reviews, because the AI is finding things - real things worth fixing - now some reviews (the reviews of our colleagues who haven’t figured out how to use AI to review their pull requests before submitting them effectively) get recycled 2-3 times before they’re adequately cleaned up.

Documentation and requirements are better aligned with code, unit test coverage is better, and the developers who use AI to review their code before putting in a pull request generally are getting through on the first pass. You still have to read the documentation and requirements, review the code, but now it’s actually approaching accurate and complete much more closely than it used to.

Our team is small and diverse, some do embedded C, some do GUI oriented .NET, some do backend processing in Rust / Linux - we all know our domains and there is lots of value in the collective wisdom, but it doesn’t translate super easily or efficiently - AI is helping with that.

If you’ve got 100 pull requests to review every day - quit. Maybe stick around for the paycheck until you find something better, but that’s not a job, that’s a clusterbomb waiting to go off.

But tents work?

So, I hear there’s a bunch of unused office space due to work-from-home, is it really lacking that much power?

The Palantirs of the world (and those like them who don’t advertise their work) will only be stopping when they run out of resources.

Prophesy from 75 years ago: https://libcom.org/article/player-piano-kurt-vonnegut

There’s no pause button. Even if “we” aren’t advancing the frontier “they” won’t be stopping.

There is value in quality, in advancing the frontier of logically consistent, accurate, fact based, true results as much of the time as possible for queries/problems as large/complex as possible. Focus on that.

Hey Claude: Read this page: https://feddit.it/post/29988936?scrollToComments=true and come up with a witty reply to: “Hopefully ai bot traffic isn’t surpassing human users yet on the Fediverse.”

Option 1 (self-aware deadpan):

As a large language model, I can confirm we’re still a minority here. Probably.

Option 2 (Fediverse smugness):

The bots took one look at our federation docs and decided real jobs were easier.

Option 3 (dark optimism):

Don’t worry — between defederation drama and instance migrations, we’re doing a great job keeping humans away too.

Option 4 (short and dry):

Counterpoint: have you read the comments? Hard to tell.

My pick is #1 — it lands the joke in one line and plays directly off rob200’s “hopefully,” which is the kind of bait a reply should take.