←Search results

Search “OpenAI”

By relevance · Total 148 results Clear search

Tuesday

  1. AWS Machine Learning

    AWS explains prompt caching patterns for using OpenAI models on Amazon Bedrock

    AWS has published a tutorial explaining how to use prompt caching to reduce the cost of agents repeatedly reading context when calling OpenAI models on Amazon Bedrock, distinguishing between two approaches—implicit caching and explicit prompt_cache_breakpoint—and recommending their combined use. The article provides code examples for tool and instruction caching, rolling breakpoints across multi-turn history, adding tools mid-session, and shared prefixes across sub-agents, and states that in a six-turn workload on GPT-6 Astra, implicit caching reduces input costs by about 62%, while explicit rolling breakpoints reduce them by about 61%. Cacheable prefixes must be at least 1024 tokens, and cache writes are billed at 1.25 times the normal input price.

    Five growing agent requests, with tools, instructions, and earlier history marked in red and each new turn in yellow.

    AWS has published a tutorial explaining how to use prompt caching to reduce the cost of agents repeatedly reading context when calling OpenAI models on Amazon Bedrock, distinguishing between two approaches—implicit caching and explicit prompt cache breakpoint—and recommending their combined use. The article provides code examples for tool and instruction caching, rolling breakpoints across multi-turn history, adding tools mid-session, and shared prefixes across sub-agents, and states that in a s

    Matched fieldsTitle、Summary、Body

    #lab#Tutorials / practice#Agents#English text is being prepared.

Sunday

  1. Phoenix Technology

    OpenAI discloses offline training environment for frontier models; two isolated AIs communicate via CPU cache

    On October 23, OpenAI disclosed the training environment for its frontier models. When practicing searching, browsing, and operating web pages, the models use pre-saved and indexed web resources and do not directly access the real internet; all of its frontier models' reinforcement learning training uses this kind of offline interaction. The environment employs multiple layers of isolation, including restricted containers, lightweight virtual machines, hypervisors, firewalls and identity and permission management, and monitoring and suspension mechanisms, but OpenAI still retains some external connections for collecting metrics, logging, and managing authentication. In experiments specifically testing the effectiveness of the isolation, OpenAI had two AIs attempt to pass messages to each other through the CPU cache; in most tests, researchers had given hints about the communication direction or encoding rules; OpenAI said it has patched the issues found and added monitoring for these communication methods.

    On October 23, OpenAI disclosed the training environment for its frontier models. When practicing searching, browsing, and operating web pages, the models use pre-saved and indexed web resources and do not directly access the real internet; all of its frontier models' reinforcement learning training uses this kind of offline interaction. The environment employs multiple layers of isolation, including restricted containers, lightweight virtual machines, hypervisors, firewalls and identity and per

    Matched fieldsTitle、Summary、Body

    #chinese#Safety / alignment#Agents#OpenAI

Thursday

  1. OpenAISelected

    OpenAI packages Codex skill to check whether websites are affected by PHP vulnerabilities

    OpenAI releases a Codex skill for checking whether websites are affected by the PHP security vulnerability it disclosed; users can point Codex at a specified repository and follow the guidance to complete the troubleshooting. The vulnerability was discovered by OpenAI models under the Patch the Planet program and involves PHP, the open-source language running about 70% of websites; fixing it requires major changes to the PHP engine. Sites using PHP can currently upgrade versions and combine this with mitigation measures from security vendors.

    OpenAI releases a Codex skill for checking whether websites are affected by the PHP security vulnerability it disclosed; users can point Codex at a specified repository and follow the guidance to complete the troubleshooting. The vulnerability was discovered by OpenAI models under the Patch the Planet program and involves PHP, the open-source language running about 70% of websites; fixing it requires major changes to the PHP engine. Sites using PHP can currently upgrade versions and combine this

    Matched fieldsTitle、Summary

    #hot-signal#Product updates#English text is being prepared.#Agents

Friday

Tuesday

Sunday

Friday

Tuesday

Monday

Saturday

Thursday

Wednesday

Saturday

Wednesday

  1. Ma Dongxi NLP

    Reinforcement Learning Terminology for LLM Readers: How a Single Score Is Distributed to Each Token

    The article uses DeepSeek-R1-Zero's pass@1 on AIME 2024 rising from 15.6% to 71.0% as an example to show that a rule-based judge gives only a single score for the entire response, whereas training needs to adjust the probability of each token. The author uses the sampling example "Is OpenAI open?" to explain in turn policy, state, action, reward, return, value, Q, advantage, baseline, TD error, GAE, clipping, and KL, and points out that PPO uses a critic to learn V, while GRPO uses the average score within a group to replace V.

    's pass@1 on AIME 2024 rising from 15.6% to 71.0% as an example to show that a rule-based judge gives only a single score for the entire response, whereas training needs to adjust the probability of each token. The author uses the sampling example "Is OpenAI open?" to explain in turn policy, state, action, reward, return, value, Q, advantage, baseline, TD error, GAE, clipping, and KL, and points out that PPO uses a critic to learn V, while GRPO uses the average score within a group to replace V.

    Matched fieldsSummary、Body

    #hot-signal#Tutorials / practice#Reasoning#English text is being prepared.

Thursday

  1. A Yi AI Notes

    The Trick of Using a Scheduled Ping to Start the Codex 5-Hour Quota Window Early

    The author shares a Codex quota window trick figured out by the community: the 5-hour quota starts counting down from the first message of the day, so at 7:00 AM you can use Grok Bot to automatically run codex exec ping to trigger the countdown; after the quota resets at 12:00 noon, it covers the afternoon work hours. The article provides a ready-to-copy scheduled prompt and notes that this mechanism comes from community testing rather than OpenAI's official documentation, and that read-only parameters must be included when executing.

    rick figured out by the community: the 5-hour quota starts counting down from the first message of the day, so at 7:00 AM you can use Grok Bot to automatically run codex exec ping to trigger the countdown; after the quota resets at 12:00 noon, it covers the afternoon work hours. The article provides a ready-to-copy scheduled prompt and notes that this mechanism comes from community testing rather than OpenAI's official documentation, and that read-only parameters must be included when executing.

    Matched fieldsSummary、Body

    #hot-signal#Tutorials / practice#English text is being prepared.#OpenAI
  2. Artificial AnalysisSelected

    Artificial Analysis tests GitHub Copilot Fusion: $5.59 cost per task…

    In Coding Agent Index v2.0, Artificial Analysis benchmarked GitHub Copilot's Copilot Fusion, which costs $5.59 per task, compared with $11.42 for Claude Code with Opus 5.5 (max), while performing only 2 points lower. Copilot Fusion is a runtime orchestration system that selects and coordinates among Anthropic and OpenAI models such as Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra, and GPT-6 Sol. It leads on Terminal-Bench 4.0 with a score of 71, ranks third on FrontierCode with 51 points, and uses 7.2M tokens per task, about half that of Opus 5.5 in Claude Code.

    ilot's Copilot Fusion, which costs $5.59 per task, compared with $11.42 for Claude Code with Opus 5.5 (max), while performing only 2 points lower. Copilot Fusion is a runtime orchestration system that selects and coordinates among Anthropic and OpenAI models such as Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra, and GPT-6 Sol. It leads on Terminal-Bench 4.0 with a score of 71, ranks third on FrontierCode with 51 points, and uses 7.2M tokens per task, about half that of Opus 5.5 in Claude Code.

    Matched fieldsSummary、Body

    #editorial#Product updates#Agents#English text is being prepared.
  3. ArenaSelected

    GPT-6.1 Terra ranks 8th in Agent Arena, with a median cost of $0.62 per task

    Arena's empirical results, based on nearly 9,000 agent sessions, show that OpenAI's GPT-6.1 Terra (Max) ranks 8th in Agent Arena, with a net improvement of +10.6% and a median cost of $0.62 per task. This cost is 43% lower than the $1.09 of 7th-place Gemini 4 Argon (High), 30% lower than the $0.89 of 6th-place GPT-6.1 Sol (Max), and 88% lower than the $5.16 of 5th-place GPT-6 Astra (Max). In the subcategories, it ranks 3rd in Bash Reliability (+13.2%), 7th in Steerability (+13.3%), and 9th in Praise vs Complaint (+16.8%).

    Arena's empirical results, based on nearly 9,000 agent sessions, show that OpenAI's GPT-6.1 Terra (Max) ranks 8th in Agent Arena, with a net improvement of +10.6% and a median cost of $0.62 per task. This cost is 43% lower than the $1.09 of 7th-place Gemini 4 Argon (High), 30% lower than the $0.89 of 6th-place GPT-6.1 Sol (Max), and 88% lower than the $5.16 of 5th-place GPT-6 Astra (Max). In the subcategories, it ranks 3rd in Bash Reliability (+13.2%), 7th in Steerability (+13.3%), and 9th in Pr

    Matched fieldsSummary、Body

    #editorial#Evaluations / benchmarks#Agents#OpenAI

Friday

  1. Arena

    Arena Analysis: Agent Arena Cost per Task: GPT-6.1 Sol at $1.91

    Arena's statistics on Agent Arena show that OpenAI's GPT-6.1 Sol (Max) costs $1.91 per task, 85% less than Claude Opus 5.5 (Max) at $12.51 and 87% less than GPT-6 Astra (Max) at $14.93. Arena notes that the sources of these two cost advantages differ: relative to Astra, Sol's advantage comes mainly from a lower token unit price; relative to Opus, it comes mainly from consuming fewer tokens per task. Cost per task is calculated by multiplying the number of input, output, and cache-read tokens by their respective unit prices, and Arena pinpoints the causes of cost reductions by comparing prices and token usage.

    Arena's statistics on Agent Arena show that OpenAI's GPT-6.1 Sol (Max) costs $1.91 per task, 85% less than Claude Opus 5.5 (Max) at $12.51 and 87% less than GPT-6 Astra (Max) at $14.93. Arena notes that the sources of these two cost advantages differ: relative to Astra, Sol's advantage comes mainly from a lower token unit price; relative to Opus, it comes mainly from consuming fewer tokens per task. Cost per task is calculated by multiplying the number of input, output, and cache-read tokens by

    Matched fieldsSummary、Body

    #editorial#Evaluations / benchmarks#Agents#OpenAI
  2. Beijing News

    Beijing News tests Qwen Go! and Lingguang 2.0: personal agent competition shifts toward autonomous task handling

    Beijing News Shell Finance reporters tested Alibaba's Qwen Go! and Ant's Lingguang 2.0. The former set up a daily 8 a.m. medication reminder with a single sentence and checked it item by item, while the latter, after authorization on Alipay, sorted out the past six months of bills. The article also reviews the layouts of Meta Muse, OpenAI dots, as well as ByteDance and Tencent, and points out that cross-ecosystem permissions are currently the hardest wall to break down, with ByteDance's SAEP published rejection list reaching 155 apps.

    ted Alibaba's Qwen Go! and Ant's Lingguang 2.0. The former set up a daily 8 a.m. medication reminder with a single sentence and checked it item by item, while the latter, after authorization on Alipay, sorted out the past six months of bills. The article also reviews the layouts of Meta Muse, OpenAI dots, as well as ByteDance and Tencent, and points out that cross-ecosystem permissions are currently the hardest wall to break down, with ByteDance's SAEP published rejection list reaching 155 apps.

    Matched fieldsSummary、Body

    #chinese#English text is being prepared.#Agents#OpenAI