Results for “context engineering”

…recognition was resolved. People discussed issues around prompt engineering, like struggles with getting the AI to adhere to detailed guidelines for modifying code and difficulties in getting the AI to rewrite original text into a format…

…competitive advantage, and LangChain introduced the concept of Context Engineering for AI agents. Reinforcement learning on LLMs shows transformative potential, and the community values AI evals and data work. Sakana AI released…

…Nemotron 3 Super: open 120B/12B-active hybrid model with 1M context and day-0 ecosystem support (@ctnzr). Claude Code outage as infra risk: frontier-model auth failure visibly disrupting real engineering workflows (@karpathy, @Yuchenj_UW). …

…to a reference in channel <#1107255707314704505> for additional context. Prompt Engineering as a Term and Job: @iiimandalorianiii finds it amusing that the term "prompt engineering" is being used like it's an established job, considering…

…(Python/TS) cover agents, memory, tools, middleware, and context engineering patterns. Announcements and guides: @LangChainAI, @bromann, @sydneyrunkle, @hwchase17, @hwchase17, @_philschmid. Hugging Face Hub v1.0 and streaming backend: Major…

…model supporting text, code, image, and video with a 64k token context window and Apache-2.0 license. OpenAI's o1-preview and o1-mini models show strong performance on long context retrieval-augmented generation benchmarks up to 128k…

…via minimalism + isolation” rather than tool sprawl (Vercel). Context engineering debate: linear chat logs vs “call stack” representations: A widely engaged post argues context-window “compaction” is partly self-inflicted by agent harnesses…

…arbitrary number of interleaved images with text and has a huge context window of 10k tokens. BigLlama-3.1-1T-Instruct: @maximelabonne presented an upscaled version of Meta-Llama-3-120B-Instruct, created through a self-merge of Llama 3 70B.…

…larger Qwen2.5‑VL‑72B from six months ago. They support 256K context, expandable to 1M, and “open vocabulary” detection. Apache‑2.0 license. Announcements and cookbooks: @Alibaba_Qwen, cookbooks, follow‑ups. Ecosystem: day‑0 support in…

…(Alibaba_Qwen). Community amplification highlights 262K native context (extendable to 1M) and competitive scores reported in tweet summaries (e.g., “82.5 MMLU-Pro,” “78.4 MMMU,” “97.2 CountBench”)—treat these as vendor/secondary claims…

…with maintaining consistent bot performance in gaming contexts. OpenAI ▷ #prompt-engineering (86 messages🔥🔥): Prompt Engineering Challenges LLMs Interaction Self-Observation in AI Chain of Thought Prompting Criticism of AI Responses…

…H Micro (3B/3B) and a 3B dense Micro variant. Key specs: 128K context, Apache 2.0, strong token efficiency. Artificial Analysis measures H Small at 23 on its Intelligence Index (non-reasoning), ahead of Gemma 3 27B (22) and behind Mistral…