Viewing profile — aabdi

If that’s such a large problem then the clear solution is to do sticky sessions? What’s the problem then? Use a cheap ds4 or Luna and do the second model net net per one shot best …

They already are? There’s a measurable performance tradeoff versus gqa so there’s reluctance. For the most part though the new deepseek v4 tech is hca and mhc and people are still …

I don’t think it would be surprising that people want to write their own kernels. A big problem with the existing engines like llama or sd is that they don’t support optimal graph …

The art of management - beyond the day to day operations - is largely organization of abstraction and incentives. As we’ve collapsed the cost of the operations then largely the poi…

Moe style router?

yes, its very good.

i wonder if we should expect this to fail by default. The meta culture has historically been known as "move fast and break things". This seems counter to a typical cloud business. …

The post suggests fear about a surge of increasing amounts of code by loops and loops of agents. I don’t know if I like the current world without it though. 80% of different teams …

The blog posts the experiences of trying to write out a new service in AWS with mostly agentic coding. The project was generally a success and achieved replacement of internal bedr…

https://blog.joemag.dev/2025/10/the-new-calculus-of-ai-based... ? in aws, some of the core bedrock services have been replaced with the new serving architecture. that thing was wri…

Probably should tell guy to read the crossing the chasm book? Seems useful in this context. Define the smallest market possible or something like that. I’m not sales though.

composer is competitive with around opus 4.5 in feeling? largely lags behind opus4.7/gpt5.4, but is respectable, and generally outperforms the glm/qwen equivalents anecdotally desp…

Consider this. U have a website. U have to translate to xx languages. Can u write it faster than an AI? If so how much faster can u do this? Is it valuable to u? Is it valuable to …

Different models do slight variants. Usually it’s done in post training to enforce behavior based on prompt. Ie. System prompt with thinking:max or low or wtv. Enforcement then goe…

Very cool article! - are other teams adopting this approach? What’s the blockers if not? - have there been problems where the models alone were not enough to debug and the devs had…

Fair, but I don’t see what case you have w this. Mind sharing? Seems niche to be both uncacheable and long context?

If this thing only has as much gpu bandwidth as the spark, it’s kinda pointles

this is hard to read... it goes all over the place. i'm not actually sure who your target audience is. there's too many side tangents. just like, structure it plz. 1. customer feel…

myself? senior engineer role is basically figuring out the business problem and getting funding. IDK i've always been able to get senior managers/managers to give me lots of leeway…

well work wise its usually for adjacent tooling. It unblocks other things, but like actual prod code, i'm always a little skeptical. For example we had this problem where we had to…

There's lots of ways. You have to upskill through the stages IMO. Write code, write w/ agent, write w/ multi agents, write w/orchestrators. My way is to just run a giant AI agent f…

Yea don’t get me wrong the words on the wikis are mostly useless. The value is in the structuring and reference graphs and links.

yes? I find ai generated deep code wikis very valuable. They provide clear walk path to read the code. Reading code raw is always painful, trying to trace the right start points, e…

+1, all the things that were said about India are true about Malaysia, Singapore, and to various degrees within Vietnam and Thailand. Yet these countries are all richer than India.…