dlojudice

It would be great if there were a plugin/extension infrastructure. For example, to write the cache and costs however and whenever I see fit

> The conditions that allow multiagent interaction to go well will be discovered one way or another: either deliberately and early, or—and by default—in production, after agents’ interactions far outnumber ours. We would prefer the former.

My master's research focuses on coordination among LLM-based agents, driven by the same motivations as the article.

One phenomenon I have focused on, though it did not appear in this specific work, is bounded rationality. Yes, agents lack social perception, they focus on one-to-one tasks and are trained in game theory and other maximization strategies. Yet, what intrigues me most is that we humans rely on heuristics precisely because our capacity to maximize gains is severely limited, a limitation that gives rise to social emergent phenomenas. As models become increasingly capable of complex reasoning, the question arises: will interactions between them give rise to the same social properties we exhibit?

great idea! pls, hnmeetup.com/[place] anyone?

How many times have people posted here about how software is no longer optimized because CPUs keep evolving, making programmers lazy? It seems things have changed. The question is: will LLMs manage to squeeze the most out of this hardware, better than compilers do? In the few tests I’ve run, yes, a lot.

Another World (Out of this world) game had its own bytecode [1]

[1] https://github.com/fabiensanglard/Another-World-Bytecode-Int...

As a programmer and founder, I think the idea is incredible, I would just change the understanding of "Code", given that what we've been hearing most lately is that "a markdown file is all you need".

I think it's not too far-fetched to think about standards, cultures, guardrails, compliance, etc. being documented, versioned, but more importantly, verifiable and applicable. In natural language, no code needed.

It feels like Auto-GPT, BabyAGI, and the like were simply ahead of their time

Researcher Tatiana Coelho de Sampaio, PhD professor, who discovered polylaminin, a drug that has proven capable of reversing spinal cord injuries in humans, worked in silence for 25 years alongside a team of biologists to achieve this breakthrough

The text reminded me of one of Veritasium's latest videos [1] about power law, self-organized criticality, percolation, etc... and it also has a wildfire simulation

[1] https://www.youtube.com/watch?v=HBluLfX2F_k

Cursor Composer appears to have this type of coupling and uses IDE resources better than other models on average.

Node-based workflow for AI generation seems to be the right approach. Being able to chain different models (Flux for realism, Sora for video, etc.) and do actual editing in between steps is way more useful than single-shot prompting. The ComfyUI comparison is obvious but this looks a bit more polished. The branching/remixing workflow could be interesting for iteration. Also being able to create a entire workflow with just one prompt would be nice.

Congratulations on your work. I spent the day working with a mix of the Composer/Sonnet 4.5/Gemini 2.5 Pro models. In terms of quality, the Composer seems to perform well compared to the others. I have no complaints so far. I'm still using Claude for planning/starting a task, but the Composer performed very well in execution. What I've really enjoyed is the speed. I had already tested other fast models, but with poor quality. Composer is the first one that combines speed and quality, and the experience has been very enjoyable to work with.

Good point. Many people (including me) switched to Apple Silicon with the hope (or promise?) of having just one computer for work and leisure, given the potential of the new architecture. That didn't happen, or only partially, which is the same.

In my case, for software development, I'd be happy with an entry-level MacBook Air (now with a minimum of 16GB) for $999.

Going further, what can I build using it? Basically, can I use Python on a Tauri project or can I use Tauri on a Python project?

+ experimental JIT compiler

this could be the beginning of something very promising

> Tinker is a flexible API for efficiently fine-tuning open source models with LoRA.

It would be great if they offered inference from the trained model as well. Ideally pay per token.

OpenRouter should be responsible for this quality control, right? It seems to me to be the right player in the chain with the duties and scale to do so.

I see some pessimism in the comments here but honestly, this kind of product is something that would make me pay for ChatGPT again (I already pay for Claude, Gemini, Cursor, Perplexity, etc.). At the risk of lock-in, a truly useful assistant is something I welcome, and I even find it strange that it didn't appear sooner.

I envision the day when I'll use a secure, high-performance browser written in Rust and fully open source. That day will come...

Wow! $1B for a bootstrapped company [1]!! Congrats!!

[1]https://www.linkedin.com/posts/gergelyorosz_im-excited-to-sh...

I wish they had published what prompt was given to Claude to improve GPT-5-mini's performance, as well as a before and after comparison of a prompt that underwent this transformation.

> a study highlighted by Apple today shows that iOS apps generated R$63.8 million ($11.7 million) in the country last year

> The study concluded that the App Store generated R$63.8 billion ($11.7 billion) for Brazilian developers last year

It seems the correct (from the original source) is billions.

https://www.apple.com/br/newsroom/2025/09/app-store-brazil-f...

I think the DBSC is on the right direction but while it generates separate keys per session to prevent cross-session tracking (Google's ultimate ad dream), the spec acknowledges a critical vulnerability: malicious sites can collaborate by attempting to guess public keys until they find matches, creating persistent cross-site user identifiers, essentially weaponizing the security feature into the ultimate tracking system that survives cookie deletion and VPN usage

I think the core question is whether hardware-accelerated translation could be meaningfully faster than software like Rosetta 2/Prism while avoiding the full dual-ISA complexity you're describing. Rather than literally implementing both instruction sets, it might be more like an ARM chip with specialized translation units and the extended ISA features you mentioned (memory ordering, etc.).

Intel's unique position with x86 IP could make this feasible where others can't, but whether the engineering effort is worth it for what might be a short-term market advantage is debatable.

Very unlikely to happen but Intel could release an Arm chip with native x86 translation. Arm and AMD IP would be needed but this would be the best chip for Windows

I'm also curious about the training process and the hardware required to train a model of this scale. The blog post mentions it's a "breakthrough in self-supervised vision AI," but I'd love to see more details on the architecture and training stability at this scale.

I got the impression that if the strategy works, the market positioning of cafes will shift from selling coffee and cookies to selling workstations with food perks.

Same here. Got this msg on the Celebras discord:

> Yeah I filed a ticket with Cursor

> They have problems with OpenAI customization

It's really cool to see Odd Lots being mentioned here on HN. It's one of my favorite podcasts. However, I think the guest for this particular episode wasn't up to the task of answering questions and exploring the possibilities of using AI in the legal world.

If this works as advertised, it could finally deliver on the promise of personalized health and wellness that we've been hearing about for years. Instead of just seeing a spike in your heart rate, you could get a notification telling you that it's likely due to stress and that you should take a few deep breaths. That's a real, tangible benefit that could justify the cost and hassle of wearing one of these things 24/7.