It’s still pretty good! Maybe the simple solution is to first prompt it to get the camera move right, without the character – just the drone point of view. Then take that video and prompt it to add the character with text or img ref.
GENERATIVE AI
-
Optimize LangChain chains with GEPA now
By
–
LangChainGEPA shout out to @bryonkuchML for contributing a PR to the GEPA repo to make it work for LangChain! You can now optimize your LangChain chains Docs: https://
gepa-ai.github.io/gepa/tutorials
/langchain_adapter_pair_sum_product_walkthrough/
… -
Nemotron-Labs-Diffusion: tri-mode model boosts accuracy and throughput
By
–
Can one model switch between three decoding modes to crush both accuracy and throughput? NVIDIA researchers (with Georgia Tech, HKU, and MIT) introduce Nemotron-Labs-Diffusion — a tri-mode language model that unifies autoregressive (AR), diffusion, and self-speculation decoding
-
Confirmed again: LLMs cannot handle the truth, says Marcus
By
–
Why LLMs rarely payoff—and what I have been saying literally for 7 years—confirmed yet again: LLMs can’t handle the truth. (Nor apparently can my critics, who keep saying I am “always wrong”, when I have been saying keeps being confirmed, over and over again.)
-
Seedance 2.0 still unbeaten in text-to-video since February
By
–
I still find it crazy that no lab has surpassed Seedance 2.0 in text-to-video, even though Seedance 2.0 was released back in February.
-
Perplexity enhances Daily Digest with customizable sources and connectors
By
–
Perplexity keeps working on the Daily Digest feature, allowing users to precisely customise from where and which data needs to be pulled from. Memory, web sources, custom instructions and many connectors will be available.
-
Opinion on DeepSeek R1, o1, and suspicious o3 benchmarks
By
–
My personal vibes based opinion on this gap – at DeepSeek R1 level I believe this was real – o1 and r1 were not that far apart. From o3 onwards, I think there's something fishy going on with the benchmarks. Open models are not bad and certainly getting better, but the utility
-
Use Codex instead of ChatGPT for better responses
By
–
You need to ask codex, not chatgpt if you want good responses.
-
Explain vs. Describe: Understanding the Nuance in AI Concepts
By
–
"Explain" vs. "Describe" These feel identical. They're not. "Explain RAG to me" gets you retrieval mechanics, why chunks are embedded, how context windows are populated, and where the architecture breaks. "Describe RAG to me" gets you a surface-level overview. What it looks
-
GPT 5.5 boosts prompt duration and confidence with new features
By
–
With GPT 5.5, /goal, autoreview and crabbox my prompts moved from ~30-60min to often 4-10h tasks and my confidence that it’s ready is much much higher. Yielding agents is a skill.