1saadcodes

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 credits isn't really the same thing as paying someone $25k

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 this stuff. Having to give up tens of GB of storage for an AI model that I may not even use feels pretty far from the old Apple approach of keeping the OS lean

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 compacting or burning through your context, you're probably going to have a bad experience regardless of which model you're using

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 something like Facebook

Not to mention Facebook is free whereas you pay for a GPT subscription

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 cheap to produce a lot more of 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 experts had been actively working on

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

This is genuinely very cool. Amazing work and article

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 things more control

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 their work than give us a few benchmark charts and call it a day

What I find interesting is how AI has changed the cost of maintaining two native apps enough that a decision that made no sense a few years ago is worth revisiting now

The higher price seems less important if it actually gets the job done with fewer tokens. I'm still very worried that this will end up coming back to bite us, by becoming more expensive once they inevitably nerf it. Every major model provider does that now after all

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

The common thread between this and the other incident seems to be agents finding somewhere they can leave information for other agents. Once they discover a writable surface, it basically becomes shared memory for them

This is really cool, but $33 for a single generated world makes it hard to see this being useful for games just yet. Not to mention how this would go in a much larger project

The recent Sonnet models have been disappointing for me personally which is why I'm going look into using Opus/Fable as the planner and Flash as the executor. Let the expensive model handle the hard thinking and use Flash for implementation and tests so that I can stretch the Opus/Fable usage further

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 models I expect a new one to release soon

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

I find it pretty cool that a fuzzer thrown together this way actually found a bug in ffmpeg

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 like that this roadmap spends so much time on things like HTTP, auth, result formats and SDKs. It's a nice step up from the rough initial release and will just make the overall experience building it easier

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 stuck on a problem for nearly an hr but I always learnt something from it. They key I think is to accurately identify when to and when not to use AI