3B active parameters, and slightly worse than GLM 4.7. On benchmarks. That's pretty amazing! With better orchestration tools being deployed, I've been wondering if faster, dumber coding agents paired with wise orchestrators might be overall faster than using the say opus 4.5 on the bottom for coding. At least we might want to deploy to these guys for simple tasks.

▲

markab21 7 hours ago | parent | next [-]

It's getting a lot easier to do this using sub-agents with tools in Claude. I have a fleet of Mastra agents (TypeScript). I use those agents inside my project as CLI tools to do repetitive tasks that gobble tokens such as scanning code, web search, library search, and even SourceGraph traversal.

Overall, it's allowed me to maintain more consistent workflows as I'm less dependent on Opus. Now that Mastra has introduced the concept of Workspaces, which allow for more agentic development, this approach has become even more powerful.

▲

solumunus 7 hours ago | parent | next [-]

Are you just exposing mastra cli commands to Claude Code in md context? I’d love you to elaborate on this if you have time.

	▲	adriand 6 hours ago \| parent [-]
		Seconded!

▲

IhateAI 6 hours ago | parent | prev [-]

[flagged]

▲

mrandish 5 hours ago | parent [-]

> just (expensive) magic trick

Related: as an actual magician, although no longer performing professionally, I was telling another magician friend the other day that IMHO, LLMs are the single greatest magic trick ever invented judging by pure deceptive power. Two reasons:

1. Great magic tricks exploit flaws in human perception and reasoning by seeming to be something they aren't. The best leverage more than one. By their nature, LLMs perfectly exploit the ways humans assess intelligence in themselves and others - knowledge recall, verbal agility, pattern recognition, confident articulation, etc. No other magic trick stacks so many parallel exploits at once.

2. But even the greatest magic tricks don't fool their inventors. David Copperfield doesn't suspect the lady may be floating by magic. Yet, some AI researchers believe the largest, most complex LLMs actually demonstrate emergent thinking and even consciousness. It's so deceptive it even fools people who know how it works. To me, that's a great fucking trick.

	▲	a_wild_dandan 3 hours ago \| parent \| next [-]
		Speaking of tricks, does anyone here know how many angels can dance on the head of a pin?
	▲	IhateAI 5 hours ago \| parent \| prev [-]
		Also, just like how in centuries past, rulers/governments bet their entire Empires on the predictions of magicians / seers they consulted. Machine learning Engineers are the new seers and their models are their magic tricks. It seems like history really is a circle.

▲

doctorpangloss 7 hours ago | parent | prev [-]

Time will tell. All this stuff will get more adoption when Anthropic, Google and OpenAI raise prices.

	▲	Alifatisk 6 hours ago \| parent [-]
		They can only raise prices as long as people buy their subscriptions / pay for their api. The Chinese labs are closing in on the SOTA models (I would say they are already there) and offer insane cheap prices for their subscriptions. Vote with your wallet.