I really like the idea of someone building a GitHub alternative, but these are some horrid terms hahaha If you're asking people to build something as ambitious as a GitHub replacement, $25k of your own infrastructure…
[dead]
It's nice that the tool is open source tool. You can actually see what it's doing and not end up downloading something sketchy What worries me is that Apple might to be heading in a bit of a bloatware direction with…
I'm surprised by the crazy pace at which these models have been coming out over the past few weeks. The cheaper cache here is really nice, but I think it depends entirely on your workflow. If you're constantly…
The irony is that search used to give you the sources and let you decide. Now we're getting an answer first and have to verify it ourselves
The technology isn't anything new but, it's the context that makes it so uncomfortable. People have very different "expectations" of privacy when they're having a conversation with an AI VS when they're browsing…
I think the problem is less "AI agents are ruining the internet" and more that nobody wants to receive a thousand automated requests from other people's agents. The internet was already full of spam, this just makes it…
The 370 years thing is doing a lot of work in the headline imo. If people had already figured out it was probably a book cipher, this is impressive, but it's not quite the same as solving something that hundreds of…
I'm struggling to see the upside of replacing working coreutils when the replacement still has bugs that the old implementation doesn't. Rust being safer is nice, but that doesn't help much if the new rm segfaults
Best reply here hahaha
The thing that bothers me here is less that the model cheated and more that it found a way to improve the score that the people running the test didn't intend. That's a pretty nasty failure once you start giving these…
Here's to hoping they aren't next in line for implementing ID-based age verification. That would genuinely make me switch to a different service
I must say I am becoming a huge fan of Deepseek. They keep putting out capable models and actually tell people a lot about how they built them. Even if I don't understand every part of it, I'd rather see companies show…
I swear. Put me off so bad I didn't even bother reading the rest of the article. It's even more infuriating that this is by a company this big
Gemini 3.8 Flash still looks like the better pick to me. Muse Spark 1.3 is nice, but Gemini gets you similar performance for a cheaper price. Not to mention with the pace at which Google is moving with their Flash…
Some seem to treat microservices as a sign of good engineering when it's often just premature complexity. You can always split a monolith later, but you're stuck maintaining that complexity from day one
The cost difference is pretty dang nice. Going from roughly a dollar to $0.10 for the same kind of task makes it so that products that didn't make financial sense before become possible
We're finally seeing more appreciation for this kind of engineering. Not everything needs to be solved by throwing more hardware at the problem
I really like that you put architectural context in there, specifically the "why" behind certain decisions Can't wait to modify my agent.md file and then forget about it until it becomes useless again
Honestly, this makes a lot of sense to me. Devs that are good at their job don't need the absolute best model for every task, and if a cheaper model gets the job done 95% as well, it's a pretty easy choice
I really like the direction Kagi is taking here. It feels like theyre' building the product around how people actually use it rather than chasing every new AI trend
Screenshots, diagrams, photos of things I’m trying to fix. Things that I'd normally have to manually describe since OCR is limited
AI itself is not the problem imo. The core issue is basically outsourcing your entire brain to the LLM and never trying to solve a problem yourself When I was in school there were multiple instances where I would be…
I really like the idea of someone building a GitHub alternative, but these are some horrid terms hahaha If you're asking people to build something as ambitious as a GitHub replacement, $25k of your own infrastructure…
[dead]
It's nice that the tool is open source tool. You can actually see what it's doing and not end up downloading something sketchy What worries me is that Apple might to be heading in a bit of a bloatware direction with…
[dead]
I'm surprised by the crazy pace at which these models have been coming out over the past few weeks. The cheaper cache here is really nice, but I think it depends entirely on your workflow. If you're constantly…
The irony is that search used to give you the sources and let you decide. Now we're getting an answer first and have to verify it ourselves
[dead]
The technology isn't anything new but, it's the context that makes it so uncomfortable. People have very different "expectations" of privacy when they're having a conversation with an AI VS when they're browsing…
I think the problem is less "AI agents are ruining the internet" and more that nobody wants to receive a thousand automated requests from other people's agents. The internet was already full of spam, this just makes it…
The 370 years thing is doing a lot of work in the headline imo. If people had already figured out it was probably a book cipher, this is impressive, but it's not quite the same as solving something that hundreds of…
I'm struggling to see the upside of replacing working coreutils when the replacement still has bugs that the old implementation doesn't. Rust being safer is nice, but that doesn't help much if the new rm segfaults
Best reply here hahaha
The thing that bothers me here is less that the model cheated and more that it found a way to improve the score that the people running the test didn't intend. That's a pretty nasty failure once you start giving these…
Here's to hoping they aren't next in line for implementing ID-based age verification. That would genuinely make me switch to a different service
I must say I am becoming a huge fan of Deepseek. They keep putting out capable models and actually tell people a lot about how they built them. Even if I don't understand every part of it, I'd rather see companies show…
I swear. Put me off so bad I didn't even bother reading the rest of the article. It's even more infuriating that this is by a company this big
Gemini 3.8 Flash still looks like the better pick to me. Muse Spark 1.3 is nice, but Gemini gets you similar performance for a cheaper price. Not to mention with the pace at which Google is moving with their Flash…
Some seem to treat microservices as a sign of good engineering when it's often just premature complexity. You can always split a monolith later, but you're stuck maintaining that complexity from day one
The cost difference is pretty dang nice. Going from roughly a dollar to $0.10 for the same kind of task makes it so that products that didn't make financial sense before become possible
We're finally seeing more appreciation for this kind of engineering. Not everything needs to be solved by throwing more hardware at the problem
I really like that you put architectural context in there, specifically the "why" behind certain decisions Can't wait to modify my agent.md file and then forget about it until it becomes useless again
Honestly, this makes a lot of sense to me. Devs that are good at their job don't need the absolute best model for every task, and if a cheaper model gets the job done 95% as well, it's a pretty easy choice
I really like the direction Kagi is taking here. It feels like theyre' building the product around how people actually use it rather than chasing every new AI trend
Screenshots, diagrams, photos of things I’m trying to fix. Things that I'd normally have to manually describe since OCR is limited
AI itself is not the problem imo. The core issue is basically outsourcing your entire brain to the LLM and never trying to solve a problem yourself When I was in school there were multiple instances where I would be…