Found 370 bookmarks
Newest
(21) Z.ai on X: "GLM-5.3 is now open-weight. Our most capable model for agentic coding and cyber defense is now available to download, run, and customize. Weights: https://t.co/v1IbWMXxg4 Tech blog: https://t.co/ekQkO83jCv https://t.co/f8XlJksKyf" / X
(21) Z.ai on X: "GLM-5.3 is now open-weight. Our most capable model for agentic coding and cyber defense is now available to download, run, and customize. Weights: https://t.co/v1IbWMXxg4 Tech blog: https://t.co/ekQkO83jCv https://t.co/f8XlJksKyf" / X
·x.com·
(21) Z.ai on X: "GLM-5.3 is now open-weight. Our most capable model for agentic coding and cyber defense is now available to download, run, and customize. Weights: https://t.co/v1IbWMXxg4 Tech blog: https://t.co/ekQkO83jCv https://t.co/f8XlJksKyf" / X
(21) Tibo on X: "Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it. This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of" / X
(21) Tibo on X: "Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it. This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of" / X
·x.com·
(21) Tibo on X: "Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it. This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of" / X
(21) Thariq on X: "a skill people at Anthropic have been using a lot recently: ELI5 /eli5 <what you want explained> "explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words" https://t.co/OZqzjAyFdT" / X
(21) Thariq on X: "a skill people at Anthropic have been using a lot recently: ELI5 /eli5 <what you want explained> "explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words" https://t.co/OZqzjAyFdT" / X
·x.com·
(21) Thariq on X: "a skill people at Anthropic have been using a lot recently: ELI5 /eli5 <what you want explained> "explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words" https://t.co/OZqzjAyFdT" / X
(21) ClaudeDevs on X: "We’re extending the 50% increase to weekly Claude Code limits through August 31. We hope to make this a permanent change to our plans, but strong demand for our models means that capacity may be tight over the coming weeks. We’ll keep you posted as things develop." / X
(21) ClaudeDevs on X: "We’re extending the 50% increase to weekly Claude Code limits through August 31. We hope to make this a permanent change to our plans, but strong demand for our models means that capacity may be tight over the coming weeks. We’ll keep you posted as things develop." / X
·x.com·
(21) ClaudeDevs on X: "We’re extending the 50% increase to weekly Claude Code limits through August 31. We hope to make this a permanent change to our plans, but strong demand for our models means that capacity may be tight over the coming weeks. We’ll keep you posted as things develop." / X
(21) Mark Kretschmann on X: "Codex tip: If you tend to switch the reasoning level often while you work, for instance between "Medium" and "High", you should reconsider! Changing the reasoning level invalidates the context cache, costing a lot more tokens as the entire context window must be regenerated. 😬 https://t.co/YslSgYbhp5" / X
(21) Mark Kretschmann on X: "Codex tip: If you tend to switch the reasoning level often while you work, for instance between "Medium" and "High", you should reconsider! Changing the reasoning level invalidates the context cache, costing a lot more tokens as the entire context window must be regenerated. 😬 https://t.co/YslSgYbhp5" / X
·x.com·
(21) Mark Kretschmann on X: "Codex tip: If you tend to switch the reasoning level often while you work, for instance between "Medium" and "High", you should reconsider! Changing the reasoning level invalidates the context cache, costing a lot more tokens as the entire context window must be regenerated. 😬 https://t.co/YslSgYbhp5" / X
(5) Tibo on X: "Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. A larger context window lets Codex retain" / X
(5) Tibo on X: "Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. A larger context window lets Codex retain" / X
·x.com·
(5) Tibo on X: "Here is how to enable a 1M-token context window in Codex for GPT-5.6 Sol. Even though we have tuned the context limit in Codex to be set optimally when it comes to performance and cost, this is a common ask, so here it is documented. A larger context window lets Codex retain" / X
(10) Povilas Korop | Laravel & AI Coding Educator on X: "I tried Qwen3.8 27B with OpenRouter (AkashML provider). Some people say it's possible to run Qwen3.8 27B locally but I don't have such hardware. Result: the simplest prompt from my LLM benchmark ran out of 15 min time I gave it and didn't finish. Also, it's REALLY expensive. https://t.co/lG4NGMiBPu" / X
(10) Povilas Korop | Laravel & AI Coding Educator on X: "I tried Qwen3.8 27B with OpenRouter (AkashML provider). Some people say it's possible to run Qwen3.8 27B locally but I don't have such hardware. Result: the simplest prompt from my LLM benchmark ran out of 15 min time I gave it and didn't finish. Also, it's REALLY expensive. https://t.co/lG4NGMiBPu" / X
·x.com·
(10) Povilas Korop | Laravel & AI Coding Educator on X: "I tried Qwen3.8 27B with OpenRouter (AkashML provider). Some people say it's possible to run Qwen3.8 27B locally but I don't have such hardware. Result: the simplest prompt from my LLM benchmark ran out of 15 min time I gave it and didn't finish. Also, it's REALLY expensive. https://t.co/lG4NGMiBPu" / X
(21) Alexander Panfilov on X: "We can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company. We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried. https://t.co/S7wN8aP3X7" / X
(21) Alexander Panfilov on X: "We can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company. We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried. https://t.co/S7wN8aP3X7" / X
·x.com·
(21) Alexander Panfilov on X: "We can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company. We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried. https://t.co/S7wN8aP3X7" / X
(7) Forward Future Brian on X: "codex tip: I always use define-goal instead of /goal. It's basically like having a master level genius AI write your goal better than you could. And it's an official OpenAI skill. You can get your prompts to run longer and your output better. Ask a high effort Sol to research +" / X
(7) Forward Future Brian on X: "codex tip: I always use define-goal instead of /goal. It's basically like having a master level genius AI write your goal better than you could. And it's an official OpenAI skill. You can get your prompts to run longer and your output better. Ask a high effort Sol to research +" / X
·x.com·
(7) Forward Future Brian on X: "codex tip: I always use define-goal instead of /goal. It's basically like having a master level genius AI write your goal better than you could. And it's an official OpenAI skill. You can get your prompts to run longer and your output better. Ask a high effort Sol to research +" / X