Search:OpenAI

By relevance · Total 150 results Clear search

Oct 152026Thursday

12:18
shao_mengOct 15 12:18
English translation is being prepared.
Matched fieldsBody
#hot-signal #Tutorials / practice #Agents #Evaluations / benchmarks
13:00
heise onlineOct 15 13:00
OpenWiki hands-on: building repository memory for coding agents
heise online tested LangChain's CLI tool OpenWiki, which analyzes a codebase and generates a linked local Markdown knowledge base, then updates it based on new diffs and commits in Git history, and makes the content retrievable through agent prompts and MCP tools. The article notes that AGENTS.md or CLAUDE.md are suitable for short rules such as install commands, tests, style conventions, and security boundaries, and in a monorepo can also be nested in subdirectory files, but they struggle to serve as a complete knowledge model for large, rapidly changing repositories.
heise online tested LangChain's CLI tool OpenWiki, which analyzes a codebase and generates a linked local Markdown knowledge base, then updates it based on new diffs and commits in Git history, and makes the content retrievable through agent prompts and MCP tools. The article notes that AGENTS.md or CLAUDE.md are suitable for short rules such as install commands, tests, style conventions, and security boundaries, and in a monorepo can also be nested in subdirectory files, but they struggle to se
Matched fieldsBody
#hot-signal #Tutorials / practice #Agents #English text is being prepared.
01:34
guardian_technologyOct 15 01:34
English translation is being prepared.
Matched fieldsBody
#hot-signal #Safety / alignment #Industry news #Tutorials / practice

Oct 162026Friday

10:34
shao_mengOct 16 10:34
English translation is being prepared.
Matched fieldsBody
#hot-signal #Tutorials / practice #Agents #English text is being prepared.
10:27
apple_machine_learning_researchOct 16 10:27Selected
English translation is being prepared.
Matched fieldsBody
#lab #Tutorials / practice #English text is being prepared.#English text is being prepared.

Oct 142026Wednesday

00:03
danshipperOct 14 00:03
English translation is being prepared.
Matched fieldsBody
#ai-news #Evaluations / benchmarks #English text is being prepared.#OpenAI

Oct 132026Tuesday

20:31
tensorzero_blogOct 13 20:31
English translation is being prepared.
Matched fieldsBody
#engineering #Tutorials / practice #English text is being prepared.#Agents

Oct 92026Friday

19:40
tensorzero_blogOct 9 19:40
English translation is being prepared.
Matched fieldsBody
#engineering #Tutorials / practice #English text is being prepared.#Agents

Oct 52026Monday

04:59
marktechpostOct 5 04:59
English translation is being prepared.
Matched fieldsBody
#ai-vertical #Industry news #Evaluations / benchmarks #OpenAI

Oct 32026Saturday

11:31
marktechpostOct 3 11:31
English translation is being prepared.
Matched fieldsBody
#ai-vertical #English text is being prepared.#Reasoning #English text is being prepared.

Oct 12026Thursday

12:21
A6 a6-051 · Cerebras：BlogOct 1 12:21
Cerebras summarizes five orchestration patterns for multi-agent workflows
Cerebras published a blog post summarizing five patterns for building multi-agent workflows: parallel generation followed by human selection, swarm parallelism, staged parallelism, sequential handoff, and separation of building from verification. Using Codex with Figma MCP to replicate a website as an example, the article states that a single agent averaged 36.5 minutes per run, 12 human interventions, and a 100% failure rate, while the multi-agent setup took 5.2 minutes, required 2 interventions, and succeeded on the first attempt; in internal testing, the sequential loop reduced human interventions by 84.3%. The author argues that multi-agent setups expand the effective context window from about 200K to over 25M, and notes that Codex Spark's speed of about 1,200 tokens/second makes parallel and verification steps feasible.
Cerebras published a blog post summarizing five patterns for building multi-agent workflows: parallel generation followed by human selection, swarm parallelism, staged parallelism, sequential handoff, and separation of building from verification. Using Codex with Figma MCP to replicate a website as an example, the article states that a single agent averaged 36.5 minutes per run, 12 human interventions, and a 100% failure rate, while the multi-agent setup took 5.2 minutes, required 2 intervention
Matched fieldsBody
#a6-editorial #Tutorials / practice #Agents #English text is being prepared.
12:21
cerebras_blogOct 1 12:21
English translation is being prepared.
Matched fieldsBody
#a6-editorial #Tutorials / practice #English text is being prepared.#English text is being prepared.
08:00
openrouter_announcementsOct 1 08:00
English translation is being prepared.
Matched fieldsBody
#company #Tutorials / practice #Agents #English text is being prepared.