LogoThread Easy
  • Explorar
  • Criar thread
LogoThread Easy

Seu parceiro completo para threads do 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

Thread

Thread

We're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github

avatar for GitHub Projects Community
GitHub Projects Community
Thu Oct 30 12:10:08
RT @doodlestein: As I've been working more today with my coding agents while they coordinate work using my new MCP Agent Mail system, I'm s…

RT @doodlestein: As I've been working more today with my coding agents while they coordinate work using my new MCP Agent Mail system, I'm s…

Former Quant Investor, now building @lumera (formerly called Pastel Network) | My Open Source Projects: https://t.co/9qbOCDlaqM

avatar for Jeffrey Emanuel
Jeffrey Emanuel
Thu Oct 30 12:09:25
3/3 settings that give you control over preserving your agents tool calls and thinking blocks

You can read more here.

3/3 settings that give you control over preserving your agents tool calls and thinking blocks You can read more here.

AI @amazon. All views personal!

avatar for GDP
GDP
Thu Oct 30 12:08:47
预热一下, 明天下午1点开始。  以后每周五都会有一场这样的圆桌会, 和大家一起交流学习。

预热一下, 明天下午1点开始。 以后每周五都会有一场这样的圆桌会, 和大家一起交流学习。

Growth Coach|Helping creators build their personal brand on X 增长教练|帮助创作者在X上打造个人品牌 公众号:PandaTalk8 X 增长群群主

avatar for Mr Panda
Mr Panda
Thu Oct 30 12:08:25
2/3 It also impacted Interleaved thinking with Tool use (off course)

2/3 It also impacted Interleaved thinking with Tool use (off course)

3/3 settings that give you control over preserving your agents tool calls and thinking blocks You can read more here.

avatar for GDP
GDP
Thu Oct 30 12:07:00
1/3 What just Anthropic did that is great for Agents?

It was a big problem to benefit from prompt caching, while using Extended Thinking, Interleaved Thinking with Tool calling etc.

They used to make a choice for users, that on every next 'user message' they used to clear "Extended thinking" blocks to manage the context length (to prevent it from growing rapidly)

However, this used to result in cache invalidation (because cached input doesn't any longer match new input - negating any benefits of caching).

Now Anthropic gives control to users on how they want old "Extended Thinking" and "Tool use" blocks want to be preserved.

1/3 What just Anthropic did that is great for Agents? It was a big problem to benefit from prompt caching, while using Extended Thinking, Interleaved Thinking with Tool calling etc. They used to make a choice for users, that on every next 'user message' they used to clear "Extended thinking" blocks to manage the context length (to prevent it from growing rapidly) However, this used to result in cache invalidation (because cached input doesn't any longer match new input - negating any benefits of caching). Now Anthropic gives control to users on how they want old "Extended Thinking" and "Tool use" blocks want to be preserved.

2/3 It also impacted Interleaved thinking with Tool use (off course)

avatar for GDP
GDP
Thu Oct 30 12:05:33
  • Previous
  • 1
  • More pages
  • 1752
  • 1753
  • 1754
  • More pages
  • 2117
  • Next