41–50 of 95 posts
Why is this article on top of HN? this is nothing breaking/new/interesting/astonishing.. The principles are super basic to get the first time you build an agent. The real problem is to get reliability. If you have reliability and clear defined input and output you can easily go parallel. THis seems like a bad 5th class homework
Why is this article on top of HN? this is nothing breaking/new/interesting/astonishing.. The principles are super basic to get the first time you build an agent. The real problem is to get reliability. If you have reliability and clear defined input and output you can easily go parallel. THis seems like a bad 5th class homework
> As of June 2025, Claude Code is an example of an agent that spawns subtasks. However, it never does work in parallel with the subtask agent, and the subtask agent is usually only tasked with answering a question, not writing any code. Has this changed since June? Because I’ve been experimenting over the last month with Claude Cide subagents that work in parallel and agents which write code (doing both simultaneousl…
Don't hide your content from people using NoScript, how about that for starters... And oh great, another Peter Thiel company booted to the top of HN, really? > "Cognition AI, Inc. (also known as Cognition Labs), doing business as Cognition, is an artificial intelligence (AI) company headquartered in San Francisco in the US State of California. The company developed Devin AI, an AI software developer...Originally, the…
Counterpoint, we'll crack autonomous coding within ~3 years, and with increases in token efficiency the speed of software development is going to go crazy. Project managers and salespeople are gonna take over big tech.
We're in the context engineering stone age. You the engineer shouldn't be trying to curate context, you should be building context optimization/curation engines. You shouldn't be passing agents context like messages, they should share a single knowledge store with the parent, and the context optimizer should just optimally pack their context for the task description.
You're not wrong. This is just a storage/retrieval problem. But ... the current systems have limits. If you want commercial success in <3yrs, are any of those ideas remotely viable?
The agentic revolution is very different from the chatbot/model revolution because agents aren't a model problem, they're a tools/systems/process problem. Honestly the models we have now are very close to good enough for autonomous engineering, but people aren't giving them the right tools, the right processes, we aren't orchestrating them correctly, most people have no idea how to benchmark them to tune them, etc. It's a new discipline and it's very much in its infancy.
Why is this article on top of HN? this is nothing breaking/new/interesting/astonishing.. The principles are super basic to get the first time you build an agent. The real problem is to get reliability. If you have reliability and clear defined input and output you can easily go parallel. THis seems like a bad 5th class homework
I would emphasize, though, that getting clearly defined input _that remains stable_ is hard. Often something is discovered during implementation of a task that informs changes in other task definitions. A parallel system has to deal with this or the results of the parallel tasks diverge.
Earlier quoted context omitted.
Apart from requiring entirely the opposite solution? With respect, if there's an AI bubble, I can't see it for all the sour grapes, every time it's brought up, anywhere.
A lot of it seems to be resistance to change. People are afraid their skillset may be losing relevance, and instead of making any effort to adapt, they try to resist the change.
It's an entirely new way of thinking, nobody is telling you the rules of the game. Everything that didn't work last month works this month, and everything you learned two months ago, you need to throw away. Coding assistants are inscrutable, overwhelming and bristling with sharp edges. It's easier than ever to paint yourself into a corner.
Back when it took weeks to put out a feature, you were insulated from the consequences of bad architecture, coding and communication skills: by the time things get bad enough to be noticed, the work had been done months ago and everyone on the team had touched the code. Now you can seeing the consequences of poor planning, poor skills, poor articulation being run to their logical conclusion in an afternoon.
I'm sure there are more reasons.
There’s both “no multi-agent system” and “multi-agent system,” depending on how you look at it. In reality, you’re always hitting the same /chat/completion API, itself has no awareness of any agents. Any notion of an agent comes purely from the context and instructions you provide. Separating agents, has a clear advantage. For example, suppose you have a coding agent with a set of rules for safely editing code. Then…
They really handing out ai domain to anyone these days.