You definitely don't want too much realism, for most games - you probably don't want to manage bathroom trips! We just assume it happens "off camera"
But when humanoid enemies behave in plainly stupid ways it's a real immersion-breaker for me. I've been gaming a looooong time, so I'm quite adept at the necessary mental gymnastics to enjoy stuff anyway... but... still... games could be better here. (And by "better" I mean "more fun")
I tried the qwen3.6-27b Q6_k GUFF in llama.cpp
and LM Studio on my M2 MacBook Pro 32GB machine
last week, and I barely get a token a second with either.
The fact that it was this slow makes me suspect it's a matter of insufficient free RAM. The entire model needs to fit into RAM (and stay there the entire time) for acceptable performance.
(not sure of exact diagnosis/fix, but definitely look in that direction if you're still having this issue when you give it another shot)
Also, there are two stages - prompt processing, and token generation. Prompt processing is notoriously slow on Apple Silicon unfortunately. If you have large context (which includes system prompts, lots of tools loaded by a harness like Claude Code, OpenCode, etc) it can take minutes for prompt processing before you see the first output token. On the bright side, the tokens are cached between turns, so subsequent turns won't be so bad.
You are using Q6 6 bit quantization; on my 32G MacMini I use Q4 and it is faster but when I use it with OpenCode, I set up a task and go outside to walk for ten minutes. Smart, capable, and slow. Still, I love using local models.
It's highly improbable that the US government has a secret team inside Anthropic and OpenAI manipulating their training regimen.
Two thoughts.
One: it would be relatively technically trivial for $GOVERNMENT_AGENCY to just monitor all the prompts + context we send over the wire to OpenAI/Anthropic/etc. That's a goldmine of sensitive personal and corporate data, no secret team needed (although, the LLM providers obviously would need to cooperate)
Two: Rather than secret infiltration teams influencing model training I think what's more likely on the training side of things is simply self-censoring by the LLM providers, so that they don't risk angering the government.
I highly doubt that China has government interlopers, secret or otherwise, inside Qwen's training team. Nonetheless, "sensitive" issues like Tiananmen Square are censored. I would imagine that much/most such censorship in China is self-censorship that doesn't leave a legal/paper trail. That's what we're in danger of seeing (more of) in America IMO.
Thus, I’ve pondered whether anything they’ve learned has changed the world / had a big impact (like on their understanding of human psychology, perhaps per region). They’ve heard phone calls, they’ve read emails, diaries get brought to court… but these are systems that would be used like diaries but also prompt users for more and more.
Yeah, at this point I think the worst-case scenario for OpenAI/Anthropic/etc is to slow down frontier model development and focus on tooling and services, as opposed to imploding completely and bursting the economic bubble. I hope?
Prevailing wisdom is that serving LLMs at a profit is achievable... it's when you factor in the cost of training them that prices get astronomical real fast.
Open-source model inference providers (who do not have to bear the cost of training) seem able to do it at much lower prices.
Of course, it's possible that they are burning through investor cash as well, and apples-to-apples comparisons are not possible because AFAIK Google does not mention the size/paramcount for 3.5 Flash.
But if the prevailing wisdom is true, I think it's actually encouraging. It suggests that OpenAI and Anthropic could perhaps, if they need to, achieve profitability if they slow down model development and focus on tooling etc. instead. If true that's probably good news for everybody w.r.t. preventing a bursting of this economic bubble.
...my opinions here are of course, conjecture built on top of conjecture....
Most of the training cost is not in the final training run, it's in all of the R&D (including salaries, equity, etc.) that it takes to get to the final training run. The actual cost of all of the TPUs (or GPUs), power, networking, storage, etc. for the final training run is significant, but it's even more expensive to have this huge R&D team doing frontier model development and using a lot of those same resources during development.
I think you're right that releasing models at a slower cadence would bring down costs to some degree, but it's not clear how much. All of these companies could significantly reduce their opex but at the risk of falling behind in terms of being at the frontier.
Not to discredit you, because you are 100% correct but tangential note about together.ai, they seem fairly unreliable with constant outages or higher than normal latency.
All I really want from a database IDE is awesome autocomplete for identifiers and keywords. (I consider SQL Server Management Studio's autocomplete to be great - if I could get that for Postgres, I'd be thrilled)
You can get part of the way there by Sublime Text to run queries and browse results. In Sublime, it's easy - you can create a custom "build tool" with (essentially) just one line of config... you're basically just piping the current file's contents to command-line PSQL: https://www.youtube.com/watch?v=tPd4m3PLVqU
Then I use the SublimeAllAutocomplete package. It works just like "regular" Sublime autocomplete except it gives you autocomplete suggestions from all open files, not just the current one - so if you have your DB schema dump in another window it will use that: https://github.com/alienhard/SublimeAllAutocomplete
Obviously, that doesn't really give you the smartest autocomplete ever but it's pretty productive for me. Tons of room for improvement though.
Sure, I perfectly understand how bars work. Like you say, it's totally possible nobody at the bar knew this woman was being harassed. Especially if this guy has plenty of experience being a creep and has gotten good at doing without attracting attention.
What I'm saying, though, is that the people around them at the bar are far more likely to be able to assist than a conference organizer who's not physically there.
"The point is that conferences should have a policy for how to deal with these kinds of situations. Those policies are probably going to depend on a certain amount of judgement from the conference organizer."
I totally agree that there need to be policies. But policies are just words, and they won't get the job done alone.
What will get the job done is looking out for each other. In social situations, particularly bars, we should all be looking out for each other, especially women, since they're disproportionally the ones on the receiving end of predatory/harassing behavior.
If she went to the bar with a group, every single one of them ought to have been looking out for each other. And yes, I've been in scores of similar situations where I and others have looked out for the welfare of others. You don't need to be an obnoxious "white knight" about it; you don't even need to be overt. Creeps tend to look for girls whose friends aren't paying attention.
Example: Your female friend is caught in a conversation with a potential El Creepo. Play dumb and introduce yourself to the guy in a purely friendly way. Heck, maybe buy a round of drinks. Just knowing that somebody noticed him will often nip things in the bud.
OK, sure. If your response is not "it's not the conference organizers problem" but "we should also try to look out for each other in social situations," I will agree wholeheartedly with that.
Yes, there are things that we should do while we are there in person. And there are things that should be handled at the conference organizer level, if there is someone who has demonstrated unacceptable behavior at the conference. And, of course, there is also the police level, for things that go so far beyond the bounds as to be able to make it to that level.
I was just concerned that a lot of people were saying things like "well, she doesn't have proof, so we should do nothing" or "well, this should be a police matter, so we should do nothing," and I thought that your comment might be along those lines, "the other people in the bar should have done something, so we shouldn't do anything." Sorry for having misinterpreted you, and yes, I agree that we should fight this kind of behavior at all levels.
As somebody who's organized community gatherings himself (and made plenty of mistakes in this area himself) I do feel that organizers play an important role as you say.
To put it in really literal terms, when I organized my first meetup, we had a mix of under- and over-21 members. I was really concerned about underage drinking. I really strongly let our members know what was expected of them. I think I stopped just shy of threatening to beat them up and/or report them to the FBI if I caught one whiff of something bad happening to anybody, especially the underage members. I definitely got the message across, at least.
While that kind of approach obviously doesn't directly scale/translate to a professional conference, I think the overarching principle is the same. The organizers set the tone, outline accountability, and (if it's a multi-year event) weed out repeat offenders. The rest is up to the community.
I've been in this conference organizer's shoes before.
On one hand, running a conference/convention is difficult enough without being asked to referee personal conflicts. It almost inevitably devolves into a he-said/she-said kind of argument.
But on the other hand, if we take that kind of an attitude, that's essentially a signal for predatory men to go ahead and harass women (or worse). That's pretty much what predatory men have been doing since the beginning of history - acting with impunity since claims of rape or harassment are almost impossible to prove if there are no additional witnesses or physical evidence.
What we've done is to stress proper conduct before the event, and if there are repeat complaints about somebody they're removed from the community permanently.
It's not a perfect process and we've given some "second chances" to people that we've later regretted.
No, that's just the signal "That's beyond my scope", a sign of professionalism. If you try to be hobby cop and judge you will fail. That's a job for the pros.
But when humanoid enemies behave in plainly stupid ways it's a real immersion-breaker for me. I've been gaming a looooong time, so I'm quite adept at the necessary mental gymnastics to enjoy stuff anyway... but... still... games could be better here. (And by "better" I mean "more fun")
reply