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

RT @haildhruv: this guy built an ai that controls his phone.

RT @haildhruv: this guy built an ai that controls his phone.

Growth Coach|Helping creators build their personal brand on X wechat official:PandaTalk8

avatar for Mr Panda
Mr Panda
Sat Nov 01 08:02:28
Codex degradation report TLDR:

- The investigation found no single root cause; rather a mix of behavior shifts and small bugs, with several fixes already shipped and more on the way.

- Older hardware underperformed in evals and was removed, and improved load balancing is rolling out to reduce latency.

- Compaction was used more often, and repeated compactions hurt accuracy; recursive summaries were blocked and a warning was added to keep chats focused.

- The `apply_patch` flow could delete and then recreate files after failed diffs, which is risky if interrupted; mitigations are in progress and a longer‑term model fix is planned.

- There was no fleet‑wide latency regression, but some sessions escalated retries and timeouts inefficiently; handling of long‑running and interactive tasks is being improved.

- A constrained‑sampling bug produced out‑of‑distribution tokens, including occasional mid‑sentence language switches in under 0.25% of sessions; a fix is rolling out.

- The Responses API added extra newlines around tool definitions; this had no measurable performance impact.

- Evals show CLI 0.45 maintained quality while reducing tokens by roughly 10%; neither `--search` nor recent prompt changes caused regressions.

- Infra analysis found low auth‑cache hit rates adding about 50 ms to tail latency; working‑directory error rates were unchanged.

- The guidance is to prefer minimalist toolsets and shorter, targeted chats, and a dedicated real‑world performance team is being formed and hiring.

Codex degradation report TLDR: - The investigation found no single root cause; rather a mix of behavior shifts and small bugs, with several fixes already shipped and more on the way. - Older hardware underperformed in evals and was removed, and improved load balancing is rolling out to reduce latency. - Compaction was used more often, and repeated compactions hurt accuracy; recursive summaries were blocked and a warning was added to keep chats focused. - The `apply_patch` flow could delete and then recreate files after failed diffs, which is risky if interrupted; mitigations are in progress and a longer‑term model fix is planned. - There was no fleet‑wide latency regression, but some sessions escalated retries and timeouts inefficiently; handling of long‑running and interactive tasks is being improved. - A constrained‑sampling bug produced out‑of‑distribution tokens, including occasional mid‑sentence language switches in under 0.25% of sessions; a fix is rolling out. - The Responses API added extra newlines around tool definitions; this had no measurable performance impact. - Evals show CLI 0.45 maintained quality while reducing tokens by roughly 10%; neither `--search` nor recent prompt changes caused regressions. - Infra analysis found low auth‑cache hit rates adding about 50 ms to tail latency; working‑directory error rates were unchanged. - The guidance is to prefer minimalist toolsets and shorter, targeted chats, and a dedicated real‑world performance team is being formed and hiring.

TLDR; I make software with AI and talk about it. Serial internet biz builder with multiple 6 & 7 figure exits. Always learning.

avatar for Ian Nuttall
Ian Nuttall
Sat Nov 01 08:02:09
RT @advancedlong: @__el__toro__ Strangely enough. I got to see some abandoned engineering offices through the rust belt. The libraries, and…

RT @advancedlong: @__el__toro__ Strangely enough. I got to see some abandoned engineering offices through the rust belt. The libraries, and…

Growth Coach|Helping creators build their personal brand on X wechat official:PandaTalk8

avatar for Mr Panda
Mr Panda
Sat Nov 01 07:59:25
🤑 月初啦,刚支付了几千佣金,感谢朋友们的支持

感兴趣帮忙分销模板的朋友们,官网右上角申请即可

🤑 月初啦,刚支付了几千佣金,感谢朋友们的支持 感兴趣帮忙分销模板的朋友们,官网右上角申请即可

🚀 The best AI SaaS boilerplate - https://t.co/VyNtTs0jSX 🔥 The best directory boilerplate with AI - https://t.co/wEvJ1Dd8aR 🎉 https://t.co/zubXJCoY92 & https://t.co/tfQf8T7gGF & https://t.co/TqRkfQj41f

avatar for Fox@MkSaaS.com
Fox@MkSaaS.com
Sat Nov 01 07:55:21
Our “Project of the Week” crown 👑 goes to Tiny8

Our “Project of the Week” crown 👑 goes to Tiny8

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
Sat Nov 01 07:54:48
大龄程序员提供吉祥三宝服务

- 保安:开动 AI,保驾护航,封堵 Bug,需求瘦身
- 保姆:手把手 1v1 咨询,帮从小白快速成长到大师
- 保洁:代码体检与整理,重构/测试/风格统一

详情请到知识星球「海哥和他的小伙伴们」

大龄程序员提供吉祥三宝服务 - 保安:开动 AI,保驾护航,封堵 Bug,需求瘦身 - 保姆:手把手 1v1 咨询,帮从小白快速成长到大师 - 保洁:代码体检与整理,重构/测试/风格统一 详情请到知识星球「海哥和他的小伙伴们」

🖥️ Indie Maker 🛠️ 星球「海哥和他的小伙伴们」 📌 油管「海拉鲁编程客」 🌸 沦为程序员的段子手/猫咪

avatar for 海拉鲁编程客
海拉鲁编程客
Sat Nov 01 07:50:46
  • Previous
  • 1
  • More pages
  • 3541
  • 3542
  • 3543
  • More pages
  • 4198
  • Next