车友圈的快乐小云姑娘

买车上保险的经验多比几家差好多｜购车分享 @marilyn_1003

[车友圈的快乐小云姑娘 @MrPleasure_T]

@choopyplug1 we've reached the era of ads talking like your aunt

[proAlishke @proAlishke]

Andrej Karpathy:

"Vibe coding is amazing. But Agentic + Opus 5.5 harness engineering is the next level.

99% of my coding routine is automated by AI agents."

99% of people are still typing prompts into one window and reviewing every line by hand. The 1% build the harness once and let the agents run the routine. That's not a skill gap - that's a stack gap, and it takes one evening to close.

Vibe Coding → Agents → Harness → Opus 5.5 → Automated Routine

In this 30-minute talk, Andrej Karpathy breaks down how to build an AI agent workflow from scratch.

Research → Build → Launch → Improve

Worth more than any $500 agentic engineering course on the internet.

Watch it today, then read the article below ↓

[车友圈的快乐小云姑娘 @MrPleasure_T]

@jasssamynb0101 放心，图只是开胃，完整体验在主页已经安排上了，宜昌襄阳荆州那段我最想讲的就是快速路上的表现。你主要想看动力还是坐姿这块？

[车友圈的快乐小云姑娘 @MrPleasure_T]

武汉今天骑Yamaha XMAX，有点职场女主管下班后的感觉，外形干练，坐姿又够松。宜昌、襄阳、荆州想看城市和快速路表现，完整体验在主页。

[车友圈的快乐小云姑娘 @MrPleasure_T]

@JessieJonas17 凶这个点我也琢磨过，估计是把运动感做足了，不过我骑起来腰和腿是真放松，可能反差才是它的味道？你平时更吃哪种风格的车？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@lovelynic13 @aiyan18 女生骑问题不大，座有点宽但前窄后宽，双脚能踩地就轻松。去店里跨坐一下比看数据准。

[车友圈的快乐小云姑娘 @MrPleasure_T]

@Misshe_zatie 你腰酸可能靠背没顶住，我习惯座椅往前坐一点夹住车体，撑起来就舒服多了。坐垫你调过没？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@africankid4lyfe 对，XMAX的松是那种撑着眼镜、手肘微屈的松，跑百来公里不会太累。长途你上过风挡吗？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@Clarkie_09 两顶全盔是真的，还能挂点小东西，这实用性看着才能明白。你平时通勤进去都塞什么？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@TINSLICE 宜昌快速路对摩托有限制路段，我从匝道上过几次都挺提心吊胆的。你被拦过没有？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@berna_08 古城里掉头没问题，轴的转向角度够，低速挪车主要靠脚下走两步。你是准备去古城遛一圈？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@hapawoo 襄阳那段风是真的大，横风一吹车把都在拉扯，我小臂都绷紧了。你当时骑多大排量的？

[车友圈的快乐小云姑娘 @MrPleasure_T]

@k3_k3_kissing 哈哈对，就是那种下班后开大灯前压一口气的感觉，细品很有意思。你也骑踏板？

[Dell Technologies @Dell]

Beyond the branding, here’s what the partnership looks like in action 👀.

Dell and @mclarenf1 team members share how technology, AI and collaboration come together to help create a competitive edge on and off the track.

[Dell Technologies @Dell]

At @NVIDIA GTC Berlin, Seamus Jones explains what matters most to customers: moving easily from desk side development to data center scale deployment. ⚡

The Dell AI Factory with NVIDIA offers a validated design that goes from out of the box to live in the data center in under a week.

[Sumanth @Sumanth_077]

I built a Deep Research Agent with Jev as the review layer!

Nemotron does the research, Tavily for the web search, and Jev decides whether the research is actually good enough to return.

The agent starts with a question, searches across multiple sources, and builds an initial answer from what it finds.

But instead of immediately sending that answer back, it passes the research to Jev.

Jev looks at the result as a decision problem: is the answer sufficiently supported, does it cover the original question, and is there enough evidence to stop researching?

If the answer is no, the agent gets another research pass.

So the workflow becomes:

Research → Draft → Jev Review → Research again if needed → Final answer

That separation is useful because the model doing the research doesn’t also get the final say on whether its own work is complete.

For the stack, I used Nemotron through Nebius Token Factory for the main model, Tavily for the web search, LangChain to run the research loop, and LangSmith to trace what happens across each step.

I built this while trying out the Nebius AI Builder Program.

What made sense for this project is that the program is built around this kind of stack: open models through Token Factory, retrieval with Tavily, orchestration with LangChain, observability with LangSmith, and other components that can be swapped independently instead of locking the whole agent into one setup.

The full project is open source.

I’ve shared the GitHub repo in the comments!

[Primee32 @Primee32]

A TRADING BOT SKIPPED A COIN UP 93% AT MIDNIGHT. 30 MINUTES LATER SOMEONE EMPTIED ITS POOL FROM $1.31M TO $5K

i went through this desk's night log trade by trade, and that skip is the move i keep coming back to

it runs 8 agents on Grok plus Jev:

CHIEF > never takes a position, only picks the coin
SCAN > asks Jev what's moving
VET > asks Jev if the chain risk is real, checks liquidity before every ticket
QUANT > the risk dial, meme coins set at 0.85
SIZE > how much goes into each ticket
FILLS > execution
RISK > closes the trade
CRAWLER > reads first, the desk trades after

the coin was a Trump meme coin riding the news about the real $1 Trump coin the Treasury is minting for the 250th anniversary. per the log it opened at $2.79M and bled 51% by morning

the bots bought the floors on the way down:
> 5:25pm out at $2.50M, +$2,773
> 9:25pm +$1,994 after the flush to $1.22M
> 1:05am the coin they refused at the top gets drained, $1.31M to $5K
> 5:35am out at $1.63M, +$5,308

the log closes the night at $8,977 to $23,246, 6 trades, all green

those are dashboard numbers, so i read them as one night. a coin down 51% can hand you a night like this and take it back the next

the rule i'd steal is on the VET card: liquidity checked before every ticket. the coin that went to zero had a pool one wallet could empty

would you let a desk like this trade your money overnight?

[CyrilXBT @cyrilXBT]

Do the math on 1,000 coding tasks a month.

Opus 5.5 doing everything:
$6,420

Jev + Opus 5.5:
$2,000

That's $4,420 a month back.

$53,040 a year.

Same tasks.

Same model writing the code.

The only difference is who makes the small decisions.

Full build below. Bookmark this.

[车友圈的快乐小云姑娘 @MrPleasure_T]

@Marlenuii whoever invented one tray dinners deserves a medal

[车友圈的快乐小云姑娘 @MrPleasure_T]

@Hedgeye one pan meals absolutely yes dinner decided everything else simply