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

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
The goal isn’t to escape work.

It’s to escape meaningless work.

The goal isn’t to escape work. It’s to escape meaningless work.

The $10M Solopreneur | Helping 100,000+ burned-out corporate professionals build six-figure, one-person online businesses at https://t.co/27OAdtwjh5

avatar for Justin Welsh
Justin Welsh
Thu Oct 30 12:02:07
Patriots unite in defense of freedom!
Huang is either a CCP spy or a bribed traitor (both are natural to assume given his chinx origins). This is obvious already. Time to deal with the viper on our breast. Unleash the ICE!

Patriots unite in defense of freedom! Huang is either a CCP spy or a bribed traitor (both are natural to assume given his chinx origins). This is obvious already. Time to deal with the viper on our breast. Unleash the ICE!

We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1

avatar for Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
Thu Oct 30 11:57:58
I feel some of my YouTube videos are "too good".

Can you be my therapists and advise, please?

So yeah, "Dear Diary..."
I think that I'm giving away too much for free.

My thinking: if I launch 2-hour video course for Laravel Daily members, I summarize it in 10-15 minute video on YouTube.

With the idea, that people would go and buy membership for full course:
- To dive deeper into the topic
- To check out the repository source code

But in last few courses, the conversion rate from YouTube to courses is unexpectedly low.

So, what if... I'm summarizing the content so well on YouTube, that people don't really even need to dive deeper. They have all the answers from a free video.

Of course, I can stop shooting these videos, or make them more like "teasers to the course" with very limited value.. but it would sound like a sleazy sales guy, I don't want to do that.

Not shoot a video about the topic at all? Also a weird options, since YouTube is still a marketing channel, and I also want to give *something* to my audience of 157k subscribers.

But, in any case, if people stop buying course memberships, I would need to stop doing YouTube videos, too, cause I would need to get back to client work, and would be too busy for YouTube.

So yeah. Any thoughts?

I feel some of my YouTube videos are "too good". Can you be my therapists and advise, please? So yeah, "Dear Diary..." I think that I'm giving away too much for free. My thinking: if I launch 2-hour video course for Laravel Daily members, I summarize it in 10-15 minute video on YouTube. With the idea, that people would go and buy membership for full course: - To dive deeper into the topic - To check out the repository source code But in last few courses, the conversion rate from YouTube to courses is unexpectedly low. So, what if... I'm summarizing the content so well on YouTube, that people don't really even need to dive deeper. They have all the answers from a free video. Of course, I can stop shooting these videos, or make them more like "teasers to the course" with very limited value.. but it would sound like a sleazy sales guy, I don't want to do that. Not shoot a video about the topic at all? Also a weird options, since YouTube is still a marketing channel, and I also want to give *something* to my audience of 157k subscribers. But, in any case, if people stop buying course memberships, I would need to stop doing YouTube videos, too, cause I would need to get back to client work, and would be too busy for YouTube. So yeah. Any thoughts?

~20 yrs in web-dev, now mostly Laravel. My Laravel courses: https://t.co/HRUAJdMRZL My Youtube channel: https://t.co/qPQAkaov2F

avatar for Povilas Korop | Laravel Courses Creator & Youtuber
Povilas Korop | Laravel Courses Creator & Youtuber
Thu Oct 30 11:53:01
  • Previous
  • 1
  • More pages
  • 1762
  • 1763
  • 1764
  • More pages
  • 2127
  • Next