与「for_sone」相关的搜索结果

드디어!!!! 누군가가 이걸 보고 그랬지. 사냥꾼 이소룡이냐고.... 절권도로 씐나게 맞아보고 싶었나부징. 근데 이 유출껀이 걸리면 나도 무사하진 못하겠지..... 목숨 걸고 유출한다 진짜.. #for_sone#

I have to say - for me it started 2 years ago. I remember the moment so well. I was on vacation in Montenegro. Early night. Everyone is asleep and I am on the balcony watching the cruise ships in Kotor bay as the horizon faded to dark. And I think it was Sonet 3.5 (don't quote me). I had just setup a plugin in NeoVim called Avante by @yetone . And it was magic. Coding with AI at the time wasn't the same - I was going function by function. I was accepting diffs one hunk at a time. But I remember that night - from 10 to like 2 in the morning - I built what I thought would have taken me a week (I was rusty and learning the stack). It was an internal tool - a partial JSON parser / repair tool - so you can take half finished JSON and safely turn it into something that would parse. It is more complicated than it sounds. Anyway. I was hooked that day. At the time I was an executive at a Fortune 50, so coding was not in my job description as such. I had hundreds of engineers... but I have to say - it relit my passions, and now as I am (hopefully) building another startup - I still love it. And I still yell at it. And constantly hunt where it is messing up the architecture and adding bloat and.... well you know how it is.

The future of Web3 won't be built on hype alone. It will be built on infrastructure that empowers developers and delivers better experiences for users. That's one reason I'm keeping a close eye on @NomismaNetwork.

KYRIE: "He deserves a lot of the praise he's gotten." COOPER: "Obviously, he's one of the greats." At Mavericks Media Day, Kyrie Irving and Cooper Flagg exchange compliments for one another as they prepare to share the court together for the first time in the upcoming season!

Trump: If I could go off script just for a second—as a special treat in honor of President Xi, I'd like to invite everyone in the room to visit through that beautiful curtain in the back. It's one year away from completion—the new ballroom that you've heard about… So in honor of you, you'll be the first people to step foot on that. This is in honor of President Xi

I see your concerns around competitive integrity with more online play in the VCT next year. We’ll share more soon about all the measures we’re putting in place to protect it. But there’s one important thing to understand: online does not mean anonymous. If you cheat in ranked, you’ll likely lose your account. Worst-case scenario, you get a hardware ID ban and can’t play VAL on that computer anymore. Now imagine doing that in a VCT Open Qualifier. All the same protections still apply, including our kernel-level anti-cheat. But there’s much more on the line. You’re competing as an individual, not just a random account. As you advance, you’ll need to verify your identity with a government ID. We know who you are. And after the Opens the competition moves to LAN anyway. So if you’re caught cheating, you’re not just risking a VAL account. You’re risking your ability to compete in the VCT altogether. And I’ll personally ban your ass for a very long time. If you have real aspirations to go pro, it is an incredibly stupid risk to take.

Introducing Headlong, an open source microharness for persistent agents: self-guided agents that think continuously. Most agent harnesses are reactive: you send a task, the agent completes it, and then it sits frozen until the next request. Cron jobs and heartbeats wake it up to run a checklist and put it back to sleep. A Headlong agent is never asleep. It keeps generating thoughts about whatever it decides is interesting, in a self-guided loop inspired by human inner monologue. Your message doesn't start a session. It's one more observation that lands in the agent's thought stream, and the agent decides if and when to reply. Headlong is built on the idea of persistent agency: continuous inner thought generation between external interactions. The agent sets its own interests and priorities, comes up with its own projects, and sometimes pings you unprompted with progress. To keep our prototype as simple and small as possible, we implemented Headlong as a microharness: a complete agent harness in under 10K lines of Bash, organized as a handful of small executables. It includes a loop that generates the next thought, shellm (a recursive language model written in Bash), a trajectory stored as a DAG of jsonl files, and context as a projection of that trajectory. We've been running one Headlong agent internally at Laude for several weeks. The whole team talks to it over Slack and Telegram, and every conversation lands in its single stream of thought. It works in its own fork of Headlong and we've pulled over 50 of its commits into main. One night, with nobody talking to it, it went back to check whether a recall process it had built was actually wired into its mind, found that it wasn't, diagnosed and fixed the bug, and verified the fix end to end. 48 minutes, no human asked for the fix or was in the loop at any point. Every step is a timestamped line in its log. Things broke too, and we wrote those up. Background thinking costs us $1 to $2 an hour, our agent stopped its own service three times by accident, and self-delegation died on day one. Details in the post. One line installs everything and starts an agent. Use a dedicated sandbox and spend-capped API key; it runs real shell commands and thinks around the clock. Headlong is research software, be careful! curl -fsSL | bash Launch post: Repo: Headlong is a @LaudeInstitute / MIT collaboration.

I think @base team should do a better job supporting and backing top projects and founders building on the chain. the trenches have been telling them for years to support memecoins and push for more CEX listings for top base coins, and they finally listened and leaned into the feedback. and the vibe already completely shifted in a matter of days. but they also need to properly back the strongest founders building on @base. after all, their motto is “base is home for builders.” @RobinhoodCrypto has been doing exactly that, and it’s one of the reasons they’re attracting so many builders to launch on their chain, with a growing number already lefr base for robinhood. @ShanAggarwal @davidtsocy @jessepollak

"My philosophy had to change to maximize this guy, James Harden... he's one of the most skilled players I have ever coached and I appreciate the trust he gave me." Mike D'Antoni shouts out @JHarden13 who is in attendance for his @Hoophall enshrinement speech! Watch the Class of 2026 Enshrinement Ceremony on NBA TV and the NBA App.