We’ve been lucky enough to have early access to this and I must say, these dudes are crushing it. What’s not shown here is the speed at which they’re moving 🤘
Very excited to finally share what we've been building!
Today, we are launching Blatent Struct, our first language model. 🚀
One thing that's always bothered us about building with LLMs is how much engineering you need around the model. Getting an answer is one thing. Making ht decision path, returns everything your application needs and doesn't break your business rules is another.
We wanted to change that.
Struct brings programmability to language models.
You can define complex, cascading decisions, conditional dependencies and exactly what each outcome must satisfy. You can also enforce business rules and permissions during inference.
And rather than stitching together multiple model calls, Struct can handle the whole decision tree in a single run.
We also spent a lot of time making sure this doesn't come at the expense of performance.
In our benchmarks, Struct achieves comparable accuracy to Claude Sonnet 5.5, at 11× the speed and over 100× lower estimated cost.
It's also over 2× faster than Jev, with higher average accuracy across 20 benchmarks. And on source-grounded extraction, it outperforms Cloudflare Clairic (87.5% vs. 81.7% across six benchmarks), at 62% lower estimated cost.
For me, the exciting part is what this enables: everything from document processing and customer support to agents that can make complex decisions while respecting the rules you've set.
This is just our first model, and there's a lot more to come.
I'd love for you to give it a try and tell us what you think. We're especially keen to hear what works, what doesn't and what you'd like us to build next.
🚀 Get started for free (up to 100m input tokens are on us) : blatent.ai
1
0
1
116
@R_Pisarczyk We have been having a lot of fun with this one. UGH I am jealous of you guys!
0
0
0
42
Maybe: Christian Rocha retweeted
Meet Prism, a specialized 8B model trained to route coding tasks to the right model in real time.
Prism chooses fast cost-efficient models for the easy stuff and bigger, smarter models for the hard stuff. We're seeing upwards 45% lower inference costs.
Now live on Charm Hyper.
Prism chooses fast cost-efficient models for the easy stuff and bigger, smarter models for the hard stuff. We're seeing upwards 45% lower inference costs.
Now live on Charm Hyper.
8
9
156
7,284
@fs_dillon @charmcli Alright, we’re back (sorry about that). There were some capacity issues from about 3:00–3:30 PM Eastern US Time. We should be back in business now.
1
0
1
23
@fs_dillon @charmcli Urgh. Yeah it is. Apologies—we're looking into it.
0
0
1
3
Maybe: Christian Rocha retweeted
We just raised a $60M Series B at a $1B valuation to build @daytonaio into the Agent Cloud.
@FirstMarkCap led the round, with all key existing investors and angels doubling down.
We're also thrilled to welcome the founders of some generational companies aboard, including bi (Shopify), @AravSrinivas (Perplexity), @BrendanFoody (Mercor), @oliveur (Datadog), @adamdangelo (Quora) and @ericsyuan (Zoom)
We're a 35-person team. But that's about to change; we're hiring across the board, and we'd love for you to join us.
@FirstMarkCap led the round, with all key existing investors and angels doubling down.
We're also thrilled to welcome the founders of some generational companies aboard, including bi (Shopify), @AravSrinivas (Perplexity), @BrendanFoody (Mercor), @oliveur (Datadog), @adamdangelo (Quora) and @ericsyuan (Zoom)
We're a 35-person team. But that's about to change; we're hiring across the board, and we'd love for you to join us.
456
200
1,405
283,969
@fs_dillon @charmcli That's odd, though it's not uncommon for code to confuse agents. Let us know if this persists; nothing’s changed on our end in terms of how inference is being served.
1
0
0
16
@ivanburazin It’s odd that everyone is chasing the same thing, because there’s an enormous amount of room to innovate
0
0
0
29
@MelkeyDev I’m enjoying they can’t do anything without their models
0
0
1
114
Considering a few different approaches for my LLM:
MoE — Mixture of Experts
MoG — Mixture of Generalists
MoHaS — Mixture of Herbs and Spices
MoE — Mixture of Experts
MoG — Mixture of Generalists
MoHaS — Mixture of Herbs and Spices
1
0
10
524
We’ve seen this before in the form of the Arts and Craft Movement in the mid-late 19th century, as a response to industrialism.
Arts and Craft did exquisite work, but it was ultimately slow to produce, incredibly expensive, and only attainable by the wealthy.
(Art history 🤘)
Arts and Craft did exquisite work, but it was ultimately slow to produce, incredibly expensive, and only attainable by the wealthy.
(Art history 🤘)
There's some senior engineers on here who, in the face of AI changing the very structures this industry is built on, present themselves as Stewards of the Craft of Programming.
Bugs the hell out for me.
They keep alluding to the virtue of doing things by hand, the value of Good Code and of craftsmanship, saying that yes, AI might change some things, but hey it won't ever change the value of something done with proper care, by hand, just like in the olden days of 2024. Most everything that was Good back then is still Good now: deep knowledge of languages and systems, good code, great architecture. You know the sermon.
And, yes, some of that *is* true. At least I think so. But we don't know, because no one truly knows what will be important in the future.
We're going through times of great change and I think the best advice to give to young people and others who want to have a job and provide value is: keep your eyes open, rethink from first principles, derive from what businesses value what you can provide; the digital world is more malleable than ever, you should rethink how you can help shape it.
All this pounding on the Bible of Good Code seems to me to be doing the opposite: it lets people feel comfortable -- what I've valued all my life is still valuable, I can rest easy -- in times when one shouldn't feel comfortable. This is a bumpy, exciting, strange ride. If you lean back you might fall off the waggon.
Let's not delude ourselves and others that we can keep doing what we've been doing. Rethink it all.
And, like I said, it bugs the hell out of me seeing senior engineers (that are secure in their career) talking as if there's nothing *really* to change, because the Fundamentals will still be valued. They might!
But it's the wrong advice to not rethink everything right now.
0
1
8
384
@andrin0ff Many years ago, when I was very young and coding Perl, I managed to teach myself regex and thought, "Yes. Now I am a real programmer."
1
0
3
81