I almost never want to talk to an AI, because text is better for almost anything. But it's nice to have that "almost" corner case covered, no?
Not to mention all the current "telephone bots" applications that could benefit from something that has actual reliable STT and can accurately grasp a number you tell it first try, or hear a natural language description of what you want and immediately bypass listing the entire menu of options one by one.
It was not paywalled for me. To your other point, sure, but you can see the normal rate of cancer in a population over time and then see the spikes in the years directly after 2001.
I hope @jolaflow can chime in here eventually, but from a brief look, my impression, besides the fact that Epiq is based on git as opposed to beads where it is optional, is that Epiq seems to be much more optimized for interactive collaboration between the user and the agents.
The graph visualization in beads surely is a neat thing for showing things, but the replay feature in Epiq should provide a similar understanding of what happened.
But again, it seems to me Epiq is the tool that better allow the user to jump right in and collaborate with the agents on the board.
(Again, this is from a brief look, so I could be missing things).
Hmm, let me check. That certainly seems wrong. Can you send me an email w/ your email so I can look into it? im cc at openrouter.ai. Or DM me on X? x.com/cclark
Houthis 'take control' of Perim Island - government source
published at 09:00
Houthi rebels have "taken control" of Perim Island in the Bab al-Mandab Strait, according to a source. Earlier, we were reporting that the group had reached the key island.
The AFP news agency also says Houthis have "taken over" Perim Island, also referred to as Mayyun, according to eyewitnesses and a local government official.
"Boats carrying armed Houthi fighters reached Mayyun Island after government forces withdrew from it yesterday," the official tells AFP.
i get that there is a vocal contingent yelling about kids using AI tools, and frankly I also think things like character.ai are potentially really harmful, but this is like saying you have to be age verified to use google
And there is another problem: LLMs generating too much code, code that is doing more than was asked. And that cannot be fixed by tests. Usually, we create tests for wanted behavior and expected exceptions. But we don't create tests for undesired behavior.
Thanks for sharing. I'm going to give it a spin for a while. The downside is you cannot comment or vote on the external site so you are always juggling the two sites for that.
toven from openrouter, leading the team working with our providers - very interested in some of the things found in the report, I dug in to the image failures specifically, and in that case we have data showing deepinfra was correctly parsing images when the endpoint went live in july, but today fails those tests. we'll work on testing images and reasoning effort etc running constantly as chris mentions in point 3.
>In one instance, over a ten-day period, Moonshot relayed almost 300,000 customer requests to Anthropic, the vast majority of which were routed to Opus. Moonshot used a proxy service network of 5,380 fraudulent accounts, most of which appeared to be located in Singapore and Japan.
The author’s comments on vision providers is especially interesting. We saw that most providers don’t provide native video url support, have high-variability in vision performance (likely due to the fact that they’re serving different quantization levels behind the same model id).
If you’re building vision-native apps, there are so many footguns in vLLM/SGLang serving configurations, let alone the routing/orchestration in providers like OR, that leave the user more confused about the model’s capabilities.
He's on the record supporting Tommy Robinson, who is one of the most prominent fascists in England. He's on the record calling for "remigration" (which is a specific word with specific meaning and context, it's not just synonym for deportation, it's a fascist dog whistle).
I think that's plenty evidence, I'm not waiting for him to tatoo "I am a fascist" on his forehead.
Also, a minimum awareness of the politics of the people producing the stuff you use is actually pretty necessary when fascism is on the rise all around the world. Might be exhausting, sure, but it's better than the alternative
I've been hearing a lot of "Amdahl's law" regarding AI - the rule that says the slowest part of a system sets the speed of what you can accomplish. On one hand, this means that AI has sped up software (so there is more software news because you can make a 20-page blog post in one prompt now), but it doesn't speed up, say, shipping hardware products that much. I guess we need to re-weight the news to include how hard it is, not just how many tokens it makes.
This sounds roughly right to me, except for "maintainability". In my experience, agents really don't like deleting code unless you explicitly ask for it. If you're not careful, you end up with new better implementations of things but with the old implementation still around in perpetuity. Humans do this too of course.
Herd animals like cattle/horses, are highly suspicious of, and stressed by, strangers. And imagine how uneasy two chimps could react when meeting for the first time.
> Framing learning from observation as somehow bad.
How about hacking accounts, using stolen credit cards, and sending data to the US silently?
> Pretending that this is bad
It is. This makes AI a 2 horse race because European labs cannot legally compete. I find it strange that people from EU cheer for that, it prevents you from having frontier level AI sovereignty.
I wouldn't assume this administration gives a shit about inflation or rising interest rates or how the rest of the economy is doing. Do you have any reason to believe they do?
Agreed, it makes sense for Finland, one of the very few places it does. But in the future of global energy supply, nuclear will be a far less serious player than it was in the 20th century.
>>I'm not against fact checking, but it absolutely felt like a punch in the gut coming from a non-dev. There was no "trust" there. She couldn't rely on my expertise, she had to go back to her "source of truth" (Claude) and asked for a second opinion on something that she wouldn't be able to verify.
This is probably how physicians feel when informed patients (whether using LLMs or not) ask questions (good or bad) during their patient encounters.
This is a weird take. Before the rise of AI/LLMs, a lot of Finland's industry was paper products and high-end manuf'ing. Both of these require a lot of electricity. Did people say the same before? No (or much less).
Not to mention all the current "telephone bots" applications that could benefit from something that has actual reliable STT and can accurately grasp a number you tell it first try, or hear a natural language description of what you want and immediately bypass listing the entire menu of options one by one.