So many people discussing things like UBI, however we selfishly create our own little projects all the time.

We need to center our shared efforts, send open source is a step on that.

Nowadays, every closed source solution should be seen as 'you are the product' type of deal.

This together with bombadil (web version pbt / Hegel / antithesis) for qa is a great advance.

We need more and more solutions like these for Agentic Coding.

I wonder if a micropayment would be detriment enough for most, even if it's just 1ct.

Above all, I'm also surprised on how those same organization are using Anthropic or OpenAI or other close source solutions for their agent harnesses instead of going for Open Source.

Malte just yesterday showed how powerful innovation with small teams can be achieved particularly in EU.

I hope they start looking for those alternatives too for their agentic systems, beyond using pi-mono.

I wonder how many here are considering that idea.

If you need determinism, building atomic/deterministic tools that ensure the thing happens.

I agree a framework is something that sounds outdated.

I also believe an orchestrator is needed. Something that abstracts you from a specific provider. Like hardware, drivers and operating systems.

Right now, my thoughts are on that line: Who will build that operating system? Who will have it in the cloud?

It needs to be robust to operate for large organizations, open source, and sit on top of any provider.

Right now we are seeing BSD vs GNU/Linux vs DOS kind of battles.

Above all, with everything that's happening in the software engineering world rn, I look at Chess as a place were we've seen it play out in the past decades. And Lichess is a big part of that.

I hope this deal helps two things: (1) Bring more people to Chess, (2) Actually, help Lichess find out a way to reward those working in it as much as they deserve.

Keep on the amazing work,

We also added pi-mono, and started using more and more other models for different tasks (Gemini, K2.5, GLM-5, you name it).

I think the problem is that most are building solutions that rely in one provider, instead of focusing self learning capabilities on improving the cost-quality-speed ratio.

For reference: https://github.com/desplega-ai/agent-swarm

ADK was (and is) exceptional, but nobody is actually making noise and pushing for it as they should. It feels like Microsoft .net back in the day.

Let's see how it goes. I'm rooting for y'all

I would love to be a bit better at it, and I did try a few of these 'battle of models' websites, but couldn't find much.

I'm interested on knowing your experience when selecting a model for different parts of your agentic SDLC.

Thus far, I'm using + sonnet for code reviews. + haiku for code searches/analysis. + flash 3.5 when LLM as judge is required + Opus to generate content. + K2.5 seldomly as alpha testing (right now for unti test generation is ok)

Ideas?

Comments URL: https://news.ycombinator.com/item?id=47611728

Points: 1

# Comments: 0

I'll give sonnet another go.

As someone that was forced to complete multiple technical engineering lettering books in middle school, when AutoCad was already common practice, and didn't really love the experience...

It did teach me a few things, and help me master writing... so maybe a good idea to keep cursive around for a few weeks? ¯\_(ツ)_/¯

(a) Transaction fees. Network fees make microtransactions prohibitively expensive. This is the real problem.

(b) 3DS & latency issues If (a) is still the same, then meaningful transactions (eg.new accounts) would require human validation of sorts, which tenders the MPP use case very small.

Is that happening to all?

Comments URL: https://news.ycombinator.com/item?id=47414511

Points: 7

# Comments: 6

Last week I had a convo with 7 separate UX/PM teams and a few seem to be very advanced with their own local set of agents for Product & UX that go way beyond the "basics" I thought of.

I would love to understand what are those principles/'starting points' that everyone should consider when taking their discipline to the next level.

Any ideas that go beyond "I coded my own design system" or "Figma MCP" but more like "I have these sets of 10 agents that evaluate, compound and etc"? Anything worth reading that's next level in the space?

For the curious: The end goal is to make every template public, https://templates.agent-swarm.dev/ My research started after reading https://elenaflores.es/aibusinesscase

Comments URL: https://news.ycombinator.com/item?id=47399055

Points: 1

# Comments: 0