Linux Dev | AI Rev Early Adopter | Gen AI\UX | Deep Agents
Phoenix, AZ
- Tweets 4,352
- Following 724
- Followers 1,987
- Likes 42,292
I had to ask the @FactoryAI Team if this was a typo
0.06x?! How can that be?
You can basically use this model all day in @droid and never hit a sub limit
GLM-5.3-Flash is the real deal - try it
This is not a typo - it’s a gift 🎁
12
9
188
32,259
Ok, this is insanely cool
@langchain is launching a model-tuning service w/@FireworksAI_HQ & @baseten
You can fine-tune your own custom model with the LangSmith Traces you already have - then compare & deploy! 👀
Hello SmithTune 🫡
Introducing LangSmith Fine-Tuning and the smithtune CLI.
LangSmith now handles the entire fine-tuning process. Use your traces to train specialized models that cut cost and latency.
Now in Public Beta. langchain.com/blog/langsmith…
6
4
25
5,180
Who has tested @tastelabs too?
Working on AI VidGen with @droid and @tastelabs
Tastelabs builds the design files and brand guide - not much shown here, but there are signs
Droid orchestrates from a prompt, skills, and MCP
1
3
15
1,978
Working on AI VidGen with @droid and @tastelabs
Tastelabs builds the design files and brand guide - not much shown here, but there are signs
Droid orchestrates from a prompt, skills, and MCP
4
2
18
4,882
Here’s the @tastelabs branding applied to the draft for finish polish 🔥
1
4
147
Cool little weekend OSS demo: Agent Seek
You .com finds pages. @typesafeai Jev re-ranks the SERP
50 questions:
74% preferred the short list vs You .com order
86% had the answer in the top 3!
Tune ranking -> less junk in context, less LLM $
3
1
19
775
Not trying to ship a search engine
Just a prototype of a tunable SERP re-ranking so agents have less context window pollution
agentseek.dev - Live Demo
1
1
149
Big fan of how @LangChain is doing these insta-webinars
The news is a few days old, @typesafeai is integrated and documented with example code in LangChains Docs 👇
And they are doing a webinar on the topic … in the same seven days 🦜
Hot topic livestream: Learn about Jev
A buzzy new model Jev, by @typesafeai, reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification tasks. It's aiming to solve the problem of slow and costly agent loops.
Next Tuesday, we’re bringing @sydneyrunkle from our engineering team at @LangChain, for a live convo on how TypeSafe AI’s model makes fast, structured decisions, where it fits in the agent loop, and how to build a harness with Jev.
Join here: events.langchain.com/webinar…
4
4
27
7,755
If you’re deep in agents, this is def worth the click
@sydneyrunkle walks through Jev & @LangChain Deep Agent Harness in a way that maps to how we actually build
Practical intel not demo-ware
🔖 Great info if you’re thinking about Agents
4
3
21
1,726
Incredible work by one of my favorite teams 🔥
If you haven’t tried @Droid yet - it’s time to see what all the hype is about!
Out of the box, it’s the best
We've raised $200M at a $5B valuation to scale self-improving software development in the enterprise.
The round brings our total funding to over $400M and more than triples our $1.5B valuation from April.
ALT Bold graphic with red background features a Factory logo, highlighting fundraising of $200M and valuation of $5B, on the way to pioneer the self-improving software category.
1
1
20
982
It’s funny watching college kids these days fall in love with socialism before they even know what earning a living actually looks like…
Someone else is paying their tuition, someone else is covering their bills, and they’re already ready to redesign the entire economy…
Lecturing the working class about how the economy should work
32
28
232
9,536
