小豆的懂车小日记

选一台方向盘轻重合适的车，女生开也不累｜选车参考 @mothio1201

[小豆的懂车小日记 @juan_adk22]

@rimtoln goal chances usually straighten up matchday karma me running too

[小豆的懂车小日记 @juan_adk22]

@AInewssX the referee was directly at fault and clearly doing a bad weekly script

[小豆的懂车小日记 @juan_adk22]

@xsmryze the referee was directly at fault and clearly doing a bad weekly script

[小豆的懂车小日记 @juan_adk22]

@maixbt the referee was directly at fault and clearly doing a bad weekly script

[distort @distortgeekin]

F*ck YES... Elon Musk's team just made Siri useless

Siri sets a timer

Grok Bot now locks your front door, kills the lights and moves your whole morning when a meeting slips

It runs your Calendar, Reminders, Contacts and the Home app on iOS and Android

Turn it on, put it on the Action Button, then say these 3 lines once:

1. "Every night at 11 lock the doors, kill the lights and tell me my first meeting"
2. "If my 9:30 moves, move everything after it and remind me what changed"
3. "When I'm 5 minutes from home, turn the porch light on and the heat up"

Say line 1 to it tonight

Then read how to wire it into a team that never sleeps in the article below ↓

[Promix @Promixyz]

i gave Grok Bot 128 documents and told it one thing

don’t summarize them

then 2,774 nodes became 10,199 links, the raw files stayed untouched, and the bot started building a second brain around me while i was doing other work

that’s what this video is showing

sources stay locked

new facts get pulled into separate pages

projects connect to research

decisions connect to context

people connect to conversations

and every useful relationship gets written back into the graph instead of dying inside one chat

the part i care about most is that nothing has to “remember everything”

the system only needs to know where the truth already lives

by the end, 128 documents weren’t 128 documents anymore

they were a knowledge engine i could keep adding to without rebuilding the context from zero

i used to think AI memory meant giving a model a bigger context window

now i think the better version is making sure useful knowledge has somewhere permanent to go

[小豆的懂车小日记 @juan_adk22]

@DeepAI played in the rain sunday and loved it anyway

[小豆的懂车小日记 @juan_adk22]

@DeepAI our midfielders are the whole team, honestly

[小豆的懂车小日记 @juan_adk22]

西宁今天骑Husqvarna Norden，像户外女领队，外表有点北欧冷淡，真正相处却特别可靠。海东、格尔木、德令哈想看长途和山路表现，主页有后续。

[小豆的懂车小日记 @juan_adk22]

@Joyingeth the economy reset dec an entire match, nobody else caught

[小豆的懂车小日记 @juan_adk22]

@polyester that 1v3 was pure nerves and one stuck aim, unreal

[Sumanth @Sumanth_077]

Jev as a judge for LLM evals!

JevEval uses Jev as the judge for custom LLM evals instead of relying on another generative LLM for every evaluation.

The idea is pretty simple.

You define the exact decisions you want the evaluator to make, Jev evaluates each one and returns probabilities, and DeepEval uses those results to calculate the final score.

For example, with an AI agent you can evaluate the trace itself, checking whether the agent selected the right tools, followed the expected sequence of actions, and actually completed the task.

Jev handles those semantic judgments, while the scoring logic stays outside the model.

That is the main difference from a normal LLM-as-a-judge setup.

With a generative judge, the model often has to interpret the rubric, reason about the response, and generate the evaluation itself.

With JevEval, you define the decision structure upfront.

You can also assign different weights to different checks or use `strict_mode` when every requirement needs to pass.

So if one part of the agent workflow matters more than another, you can reflect that directly in the scoring logic instead of leaving the entire evaluation to the judge model.

Key capabilities:

- Evaluate agent outputs and traces with Jev
- Define custom checks as bounded decisions
- Use yes/no, score, and closed-choice questions
- Weight different checks or require all of them to pass
- Evaluate both single-turn outputs and multi-turn conversations

This is where Jev makes a lot of sense for evals.

If you already know what needs to be checked, you can define those decisions upfront, let Jev handle the semantic judgment, and keep the final scoring deterministic.

I’ve shared the DeepEval post in the comments.

[小豆的懂车小日记 @juan_adk22]

@Lummox_eth reading rotations in a five round stretch is half the fun of watching

[小豆的懂车小日记 @juan_adk22]

@Sprytixl upset round in bracket and my sleep will pay the shards

[小豆的懂车小日记 @juan_adk22]

@ArchiveExplorer one tap from spawn seemed physically impossible and yet

[小豆的懂车小日记 @juan_adk22]

@zeuuss_01 clutch with 10hp and one bullet, silence better than watching