小柚陪你学汽车

车内眼镜盒这个设计，老司机都知道有多方便｜汽车日记 @mothio1201

[小柚陪你学汽车 @reallwett]

@alcaldiagye Cool stuff

[小柚陪你学汽车 @reallwett]

@Sai60012 @grok Bookmarked this

[Ackerman @Yarilo7brigada]

THIS IS F*CKING INSANE

THE MOST EXPENSIVE MISTAKE IN MULTI-AGENT TEAMS: A BOT SAYS “DONE” WITH NO PROOF

you built a shared brain. your bots ignore it, write “done”, and lose context on every handoff. without a verification layer, a Shared Brain is just a pretty folder nobody opens

6 repos that close this gap:

01 run → state in markdown, “done” only with evidence in the log, work resumes from a Handoff block instead of yesterday’s chat
https://t.co/yNSZ8VaMBb

2 x-harness → the agent fills out a completion card, and a separate read-only verifier decides whether to accept the claim
https://t.co/oVannEggOx

3 Agent Spartan Protocol → one markdown task file as the source of truth for handoffs between agents. review always goes to the host that didn’t do the work
https://t.co/1oORn8UPIX

4 handover-mcp → local state handoff when you switch sessions, models, or agents, with connectivity, completion, and continuity checked separately
https://t.co/cfRehMDth9

5 beads → a dependency-graph issue tracker built as memory for coding agents. the agent sees what’s already done and what’s blocking
https://t.co/IgfGE363X4

6 superpowers → a skill library that includes verification-before-completion: proof first, then “done”
https://t.co/kgq3HxJeUF

the rule is simple, completion is accepted, not claimed

how to add verification to your bot team in one day ↓

[小柚陪你学汽车 @reallwett]

@DailyDoseOfDS_ toms left dying straight up made garden guilt despite watered today

[小柚陪你学汽车 @reallwett]

@cyrilXBT basil sun went dud one plant that shelf hits honestly agree

[小柚陪你学汽车 @reallwett]

@Yarilo7brigada basil sun went dud one plant that shelf hits honestly agree

[Niche trader @OLeksa_trader]

THIS FUCKING GUY TURNED GROK INTO HIS PERSONAL TRADING ASSISTANT.
$270 AN HOUR USING AI. 🤯

Check: https://t.co/EHckQIYkdh

Instead of watching charts all day, he uses Grok to analyze market setups, spot patterns, and follow a simple trading strategy.

Here’s his workflow ↓
→ Feed market data into Grok
→ Ask it to identify specific setups
→ Filter opportunities using strict rules
→ Confirm the entry signal
→ Set stop-loss + take-profit levels
→ Track trades automatically

The crazy part?

He claims his AI-powered system can generate around $270 per hour when market conditions are right.

But the real lesson isn’t the $270.

It’s how he uses AI.
He doesn’t ask Grok to magically predict the market.

He gives it a clear set of rules.

Then uses AI to speed up the analysis, follow a consistent process, and make trading more systematic.

No magic.
No guaranteed profits.

Just a trading strategy + AI + disciplined execution.
Here’s the exact strategy he uses

Comment « AI TRADING» and I’ll send you the website.

[小柚陪你学汽车 @reallwett]

@NasdaqExchange seeds bought everything basil now work outdoor

[Elon Musk @elonmusk]

Yes

[小柚陪你学汽车 @reallwett]

@F1 container water bottom crack care daily tree up here scale

[小柚陪你学汽车 @reallwett]

@fingersman 对，低扭巡航的声浪不是那种炸的，是沉在底下的稳。等我主页后续发视频，你听着判断下是不是那个味儿。

[小柚陪你学汽车 @reallwett]

延安今天碰到宝马R 18，车身长，发动机横向撑开，停着就很有存在感。西安、宝鸡、咸阳想看它巡航起来什么感觉，主页有后续。

[小柚陪你学汽车 @reallwett]

@josieeebb 照片拍出来确实差点意思，横向那台拳击手发动机得站跟前才能感受到它有多撑。你要是来西安，可以找个地方一起蹲一台。

[小柚陪你学汽车 @reallwett]

@hicksmelissa77 对，R 18就是低速滑过去那种感觉，声音沉但不吵，西安环城路那氛围配上它挺合适。

[小柚陪你学汽车 @reallwett]

@kingpops 哈哈对，尤其这个横向的拳击手发动机，站旁边看比照片夸张多了，你要是现场看估计也得回头。

[小柚陪你学汽车 @reallwett]

@therealsexy17 宝鸡这边碰到了一定多拍，巡航那段比停着还有意思，你们那边骑这个的多吗？

[小柚陪你学汽车 @reallwett]

@sumsub layer up and skip the wool, soft synthetic all day

[Sumsub @sumsub]

About 2,000 years ago, traders were already facing a question we’re still dealing with today: how do you trust someone you’ve never met? 🧐
That question is where our new podcast, Trust Forward, begins.

In Episode 1, our host Mary-Ann Ochota travels to a Roman trading site in Yorkshire with archaeologist @diggingthedirt, uncovering a world where people haggled over pottery, exchanged silver coins and had to decide, face to face, whether the person across from them could be trusted.

But how did those individual moments of trust grow into something much bigger? How did we go from trusting a stranger in a marketplace to trusting currencies, banks and eventually numbers on a screen?

Cryptographer and author @schneierblog joins the conversation to explore how societies learned to build trust between strangers at scale, while cognitive neuroscientist Professor @sophiescott looks at the other side of the story: what actually happens in our brains when we decide whether someone is trustworthy.

It all leads back to one surprisingly complicated question: what is money, really — and why do we trust it?

🎙 Listen to the first episode now: https://t.co/i52Q7A3hDP

[CyrilXBT @cyrilXBT]

OPUS 5.5 SHOULDN'T BE DOING THE WORK.

It should be writing the PLAN.

Claude Code workflows let Opus write a script that runs a whole swarm of agents in the background.

Opus plans.

Haiku 5.5 scans every file in parallel.

Sonnet 5.5 makes the fixes.

A verifier checks every finding.

Opus only sees what survives.

Your expensive model never reads 100 agent transcripts again.

Setup prompt below 👇

[Vogue Runway @VogueRunway]

The star wore a custom Chanel gown that nodded back to her glitzy red-carpet look at the 1997 Oscars. https://t.co/Er1IUi8oJA