与「JUSTRIGHT」相关的搜索结果

This "Little Maldives" hidden in Yichun Jing'an, China, is just right for a weekend trip! 这个藏在中国宜春靖安的“小马尔代夫”，周末游刚刚好！ #CharmOfJiangxi#

Does it make you “far right” to want: - vetted immigration - no digital ID - lower taxes - no two-tier policing - free speech - pedophiles out of office - lower cost of living MSM and politicians will call these ladies far right. Does this sound far right to you or just right?

一口奶，一口咖啡， 最喜歡它們在嘴裡慢慢融合的那一刻。 像今天的心情一樣，甜一點、濃一點、剛剛好。 One sip of milk, one sip of coffee — I love the moment they slowly blend together. Soft, rich, and just right.

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

I spent more test time compute and realized that my micrograd can be dramatically simplified even further. You just return local gradients for each op and get backward() to do the multiply (chaining) with global gradient from loss. So each op just expresses the bare fundamentals of what it needs to: the forward computation and the backward gradients for it. Huge savings from 243 lines of code to just 200 (~18%). Also, the code now fits even more beautifully to 3 columns and happens to break just right: Column 1: Dataset, Tokenizer, Autograd Column 2: GPT model Column 3: Training, Inference Ok now surely we are done.

+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits. On top of context engineering itself, an LLM app has to: - break up problems just right into control flows - pack the context windows just right - dispatch calls to LLMs of the right kind and capability - handle generation-verification UIUX flows - a lot more - guardrails, security, evals, parallelism, prefetching, ... So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.

Spring is here! The Monad community stretches lazily, opens its arms, and invites every family member on a spring adventure! 🌸 This is a living, breathing family that grows with you. It accompanies you in exploration, learning, and pushing boundaries. When you're lost, it guides you; when you progress, it cheers for you.🌞 It’s not just a fleeting buzz; it’s the force that helps you go further. 💜 While the spring breeze is just right, let’s set off together with Monad! 🌈 @monad_xyz @monad_zw @RealNadsClub @JohnWRichKid @KinglouiEth @_gvan @cryptunez @thisisfin_ @kryptobaby777 @wagmigently @billmondays @doctorpreballin @keoneHD

FIRST STOP with Captain @layzhang The atmosphere is just right tonight! Let's be together as much as we can! Jump into summer and start all over again! Let's dance, dance, dance~ #LAY_GRANDLINE2# #Malaysia#