LogoThread Easy
  • Explorar
  • Componer hilo
LogoThread Easy

Tu compañero integral para hilos de Twitter

© 2025 Thread Easy All Rights Reserved.

Explorar

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

It will be a sweet time when we can run open models locally and have cursor use local models. That’s when I’ll buy a Mac Studio just to run agents all day for me.

It will be a sweet time when we can run open models locally and have cursor use local models. That’s when I’ll buy a Mac Studio just to run agents all day for me.

Founder 📈 @parqetapp Host of 🎙 @minimalempires Prev. @stripe

avatar for Sumit Kumar
Sumit Kumar
Sat Dec 20 17:22:01
RT @bravo_abad: Machine learning for predicting which MOFs can actually be made in the lab Metal-organic frameworks (MOFs) are among the m…

RT @bravo_abad: Machine learning for predicting which MOFs can actually be made in the lab Metal-organic frameworks (MOFs) are among the m…

Founder and CEO @deepforestsci. Creator of @deep_chem. Author @OReillyMedia. @stanford CS PhD. https://t.co/7LDcegrCsc

avatar for Bharath Ramsundar
Bharath Ramsundar
Sat Dec 20 17:21:51
railway is one of my favorite pieces of software it just works, it’s gotten better and cheaper over time, intuitive, etc highly recommend

railway is one of my favorite pieces of software it just works, it’s gotten better and cheaper over time, intuitive, etc highly recommend

making complex metal assemblies for fast moving companies | Founder at RMFG

avatar for Kenneth Cassel
Kenneth Cassel
Sat Dec 20 17:20:32
there’s a lot of low (and later high) hanging fruit in agent engineering without touching the model weights with Reflective Optimization with Claude Code: - just start by storing traces - let agent do Tasks, everything autologs in LangSmith - pull down a few groups of traces for good/bad runs - let agent read Traces and find patterns in where things went good/bad (improve prompts, edit tool desc, make skills) - loop, analyze yourself this is a really accessible loop today! at LangChain I love this loop, because it gets some momentum and gives us an immediate signal for improving stuff systematically without guessing infuse your taste and domain knowledge from there, but great place to start

there’s a lot of low (and later high) hanging fruit in agent engineering without touching the model weights with Reflective Optimization with Claude Code: - just start by storing traces - let agent do Tasks, everything autologs in LangSmith - pull down a few groups of traces for good/bad runs - let agent read Traces and find patterns in where things went good/bad (improve prompts, edit tool desc, make skills) - loop, analyze yourself this is a really accessible loop today! at LangChain I love this loop, because it gets some momentum and gives us an immediate signal for improving stuff systematically without guessing infuse your taste and domain knowledge from there, but great place to start

agents, harnesses, and evals @LangChainAI, prev @awscloud, phd cs @ temple

avatar for Viv
Viv
Sat Dec 20 17:18:07
Having a well optimized twitter is still a superpower: - Fastest news feed in the world - Thought-stream from smartest people - Noticed by world leaders if tweet goes viral - Access to unique closed-door debates - Hilarious simulation

Having a well optimized twitter is still a superpower: - Fastest news feed in the world - Thought-stream from smartest people - Noticed by world leaders if tweet goes viral - Access to unique closed-door debates - Hilarious simulation

stealth consumer bio | prev founding team @a16z @speedrun | writer of the bird’s nest, https://t.co/3fgQ6avUsx

avatar for robin
robin
Sat Dec 20 17:17:50
RT @TheChiefNerd: TIM DILLON: “I'm giving advice to people now that live in this country. Choose the p*dophile you agree with … Who is the…

RT @TheChiefNerd: TIM DILLON: “I'm giving advice to people now that live in this country. Choose the p*dophile you agree with … Who is the…

🇪🇺https://t.co/NdorAWqJC3 @euacc 📸https://t.co/lAyoqmSBRX $118K/m 🏡https://t.co/1oqUgfD6CZ $36K/m 🛰https://t.co/ZHSvI2wjyW $43K/m 🌍https://t.co/UXK5AFqCaQ $15K/m 👙https://t.co/RyXpqGuFM3 $14K/m 💾https://t.co/M1hEUBAynC $6K/m

avatar for @levelsio
@levelsio
Sat Dec 20 17:13:20
  • Previous
  • 1
  • More pages
  • 255
  • 256
  • 257
  • More pages
  • 5634
  • Next