elar_verole

I mean it depends exactly what you do. But for me for example, dumping HUGE pdf docs for external systems / vendors in a folder and just.... asking claude about what I want to know works amazingly well (while giving access to the folder obviously), it never failed me or gave me wrong info since the latest few models.

I'd imagine just that could already be pretty useful for your line of work ? That does require to have a claude subscription and using Opus 5.5 for it to be worth it or cost efficient.

Then you can compound this: give it access to more of these docs, have it memorize, create skills on where to find what, then move on to more and more "vague" prompts and you'll notice it knows what to search for, where, and how.

Quickly enough you can ask it to generate an artifact explaining really complex stuff super succinctly and gain a ton of time. You can ask it for links to its sources in your docs for each point it makes in order to easily confirm it doesn't make anything up etc...

But to reach that point, you might need to go step by step so you know you can trust it because it didn't fail you on the smaller, easily verified steps you tried early on.

I wholeheartedly agree. To clarify my position, I don't think having these amazing models mean we should replace everyone, quite the opposite.

I do think they are close enough to the stage where people will be replaced, even though it's not the right or correct thing to do, and that we need to move on from the "denial" phase quickly enough so our societies can adapt / regulate / legislate while not too late.

It is very good at programming. Because programming is a lot of language, and these tools were also made by programmers and post trained to be good at it.

But I assure you it's even "better" (not really but the task is so much easier) at making your spreadsheet look nice and compare actuals vs forecast for your budget than a complicated programming task. It will just one shot it, and it will be objectively correct, all in a very short time. But these non tech people don't know they can use an agent, they have asked one question in the chat interface with 0 context about what they're trying to do, and conclude they are not good enough.

I'm not saying everything is replaceable by AI - and by the way I don't want anything to be replaced by it, but I believe it will happen - just that some people don't realize yet how "trivial" their job is to modern models.

It's very true to me. Another effect I noticed in less tech inclined jobs (but still office jobs) is that they're still convinced "their" special job is not possible to automatize, because it's too complicated. Mind you some of them have really simple jobs, bordering simple data entry in excel. They tried chatGPT once or twice one year ago and don't realize what's coming for them. Since in tech circles we're the first ones to optimize and use new technologies we are most aware of the huge leaps that happened and the current impressive capabilities but lot are still oblivious to it.

Yes agreed. That's kinda what I wanted to highlight. There is no real political pluralism for people in the US which must suck

You gotta love that only 65% of the """leftist""" party's voters in the US have positive views on Socialism.

Replace all ads with beautiful classic paintings, get closer to see info about (title, artist, year)...

There's something to it

I mean one of these agents figuring out it can order free compute on the cloud, install a free codex account and a cron to regularly wake itself up with a specific goal and building from there is definitely not that far fetched considering what they can do.

What's your point ? You think nothing happened and this is a complete lie for marketing purposes ?

didn't notice your comment so posted a similar one - but yeah this is a very high level of inexperience to me... You'd think they would have some of the greatest security experts in there

I find it extremely naive to think that limiting requests to "GET" is an actual security layer. Anyone who's worked with any kind of legacy/old-ish system would know this is definitely not enough.

Pretty sure it's a US thing since it's available here in France. What exactly is down, idk

No issues on claude or chatgpt in France, must be some US specific infrastructure going down ?

Should have been called YouMan !

It's called "OVNI(s)" (French equivalent for UFO(s))

Just watching him play POE should show you he's not the genius you think he is

I'd argue that your colossal overreaction to a small invitation to discuss a somewhat interesting hypothetical is what warrants medical attention

I think this can't work because an LLM needs too much data, and before the internet there probably just wasn't enough to get close to what we have now

>Unless maybe the CPU vendors - are making these powerful CPUs knowing they will be rented by the thread

I think you answered your question already. AWS buys it -> you get instances that use a small part of the huge CPUs basically.

Working on our game which is a twin stick shooter with auto-battler / TFT style shops and upgrades. We have a demo out: https://store.steampowered.com/app/4805740/runz_Demo/

going fine, good reviews + average playtime isn't bad at all for only a demo, but it's frustrating to just struggle to get eyes on it.

Thank you, been saying that everywhere this "Gotcha" argument comes up, the internet DID become a cesspool of spam and fake content. That's literally what they were scared about.

Several things:

https://github.com/openclaw/wacli for WhatsApp,

https://github.com/diamondburned/arikawa for discord, and

https://github.com/mautrix/meta for messenger.

There was a bit of initial setup extracting tokens for messenger and discord I believe, but now it's smooth sailing. Some issues sometimes correctly mapping ids to usernames / convos make it so some conversations are duplicated for messenger, but when I have time I think some smart reconciliation heuristic will be able to take care of it.

It's great !

My favorite is: https://github.com/theo-sardin/instant-switcher

Instant windows switcher with custom shortcuts and instant "opt+tab" and trackpad switching. Simple does exactly what I need it to do (just bypasses the slow window switching that is annoying), with no additional features or bloat.

I've also done a TUI that combines my messages from WhatsApp + messenger + discord which is pretty handy at work.

Yeah, this seems to be the easiest path for overall agents efficiency in the short term

I just thought it was interesting to remind everyone how mind boggling chatGPT first public version was to everyone, as it was released 3.5 years ago.

Nothing came close before it, and now we have agents / models that are not even comparable in terms of capabilities and "intelligence".

We'll see where it goes from here !

Sometimes feel like I'm the only one still using it around me, but the service is still great and functional

Started some playtests for our game with my brother (I mean we don't REALLY have testers yet, we need a bit more work first because right now it's lacking 1 or 2 core elements of the fun / gameplay loop): https://srdnvntrz.itch.io/runz

also created and got our steam page validated: https://store.steampowered.com/app/4704420/runz/

We've been moving fast, it's our second project and we hope to deliver something people find fun and appealing, at least for our friends !

We suck at marketing though (such is the game dev burden), but we're having fun and learning stuff, which is what it's all about I guess.

Yes, I love how everyone uses this argument, when what they were saying was among the lines of "GPT-2 would make it too easy to generate spam, deepfakes, content to manipulate opinion..." (not the actual quote but something like that). Turns out it was completely correct if you look at the state of the internet right now.

Obviously, they still overhype and oversell this end of humanity stuff, but this argument regurgitated ad-nauseam is not THAT great of an example when you think about it.

People need heroes. It's like the Keanu Reeves or Musk era, all the ""badass"" stories about this or that soldier / local hero / w/e that are very often overblown and get further and further away from the initial facts every time they resurface. No hate here, just noticing there is a weird visceral need to distill stories to their most essential, good vs evil, and the Tesla v Edison thing embodies this perfectly I think.

Makes sense