Home
Language
English
Türkçe
Bahasa Indonesia
About
Privacy Policy
Terms of Service
Pricing
Sign In
Download All
Share
jerrychaox
@jerrychaox
Ex-Bytedance
Joined September 2018
120
Following
17
Followers
85
Posts
jerrychaox
@jerrychaox
about 11 hours ago
@chasen_liao
写个hook不就好了
jerrychaox
@jerrychaox
about 12 hours ago
@GenAI_is_real
分屏开一个PI 然后配上deepseek或者gemini 让他��给我传话给Claude🤣🤣
jerrychaox
@jerrychaox
1 day ago
@BtreeWw
AI的SSOT有时候和人不太一样
jerrychaox
@jerrychaox
1 day ago
Fable处理大数据开发,竟然连先导出一��完整的Raw再处理都不会
jerrychaox
@jerrychaox
1 day ago
@RonVonng
supabase竟然��没有正式支持duck扩展,怎么蹦啊
jerrychaox
@jerrychaox
5 days ago
@agentmail
@bot
i got banned when I use default domain of agent mail to sign in the app
jerrychaox
@jerrychaox
6 days ago
@DottChen
@modal
可以看下 bwrap
jerrychaox
@jerrychaox
6 days ago
@akazwz_
deepseek多模态 + 飞书 + 自己注册刷社媒
jerrychaox
@jerrychaox
7 days ago
@FiniYang
在code-mode上表现怎么样,比较在意agent能在harness层面一次编排多���骤rpa
jerrychaox
@jerrychaox
7 days ago
@orca_build
nice, but what's going on my Workspace panel does not show all my agent
jerrychaox
@jerrychaox
7 days ago
@I_am_oil_oil
@xin_pai88825
恭喜 兄弟!
jerrychaox
@jerrychaox
7 days ago
最近经常需要做一些云端的agent,利用比较便宜的模型完成特定的任务 他们的开发过程,不知道算不算蒸馏,因为都是用本地的5.6 Sol或者Fable开发 过程中如果小模型干的不好,经常的做法是让5.6 Sol查看5.6 Luna的上下文呢,然后让Sol对Luna进行慰问,询问他遇到什么困难,从而得出优化方案
jerrychaox
@jerrychaox
8 days ago
@GenAI_is_real
+1,我的ai chat的需求都会在google浏览器的chat展开,而不是gpt和claude
jerrychaox
@jerrychaox
8 days ago
@bojie_li
damn 是类似Google的BBR的思路吗
jerrychaox
@jerrychaox
8 days ago
LOL
Sakshi
@Sakshi50038
9 days ago
Who's gonna tell vibe coders about... > Rate Limiting > Caching > Load Balancing > Reverse Proxies > API Gateways > CI/CD > Docker > Kubernetes > Service Discovery > Circuit Breakers > Timeouts > Retries > Exponential Backoff > Idempotency > Message Queues > Pub/Sub > Event-Driven Architecture > Distributed Transactions > Saga Pattern > Dead Letter Queues > Cron Jobs > WebSockets > Long Polling > Server-Sent Events > Database Indexing > Query Optimization > N+1 Queries > Connection Pooling > Read Replicas > Sharding > Partitioning > Replication > Leader Election > CAP Theorem > Eventual Consistency > Optimistic Locking > Pessimistic Locking > Distributed Locks > Race Conditions > Deadlocks > Memory Leaks > Garbage Collection > Thread Safety > Backpressure > Autoscaling > Horizontal Scaling > Vertical Scaling > CDN > Edge Caching > Cache Invalidation > Feature Flags > Blue-Green Deployments > Canary Releases > Rolling Deployments > Rollbacks > Health Checks > Liveness & Readiness Probes > Monitoring > Logging > Distributed Tracing > Metrics > Alerting > SLOs > SLIs > Error Budgets > Observability > Secrets Management > IAM > OAuth > JWT Rotation > TLS > Encryption at Rest > Encryption in Transit > WAF > DDoS Protection > CORS > CSRF > SQL Injection > XSS > SSRF > Database Migrations > Schema Versioning > Disaster Recovery > Backups > Failover > Multi-Region Deployments > Chaos Engineering > Cost Optimization > Cold Starts > Serverless Limits > Latency > Throughput > P99 Latency > Tail Latency > Network Partitions > Clock Skew > DNS > TCP vs UDP > HTTP/2 & HTTP/3 > gRPC > Webhooks > API Versioning > Semantic Versioning > Infrastructure as Code > Terraform > Helm Charts > Build Caching > Dependency Hell > Production Incidents > On-call > Postmortems ...until the app gets its first million users.
See More
jerrychaox
retweeted
Sakshi
@Sakshi50038
9 days ago
Who's gonna tell vibe coders about... > Rate Limiting > Caching > Load Balancing > Reverse Proxies > API Gateways > CI/CD > Docker > Kubernetes > Service Discovery > Circuit Breakers > Timeouts > Retries > Exponential Backoff > Idempotency > Message Queues > Pub/Sub > Event-Driven Architecture > Distributed Transactions > Saga Pattern > Dead Letter Queues > Cron Jobs > WebSockets > Long Polling > Server-Sent Events > Database Indexing > Query Optimization > N+1 Queries > Connection Pooling > Read Replicas > Sharding > Partitioning > Replication > Leader Election > CAP Theorem > Eventual Consistency > Optimistic Locking > Pessimistic Locking > Distributed Locks > Race Conditions > Deadlocks > Memory Leaks > Garbage Collection > Thread Safety > Backpressure > Autoscaling > Horizontal Scaling > Vertical Scaling > CDN > Edge Caching > Cache Invalidation > Feature Flags > Blue-Green Deployments > Canary Releases > Rolling Deployments > Rollbacks > Health Checks > Liveness & Readiness Probes > Monitoring > Logging > Distributed Tracing > Metrics > Alerting > SLOs > SLIs > Error Budgets > Observability > Secrets Management > IAM > OAuth > JWT Rotation > TLS > Encryption at Rest > Encryption in Transit > WAF > DDoS Protection > CORS > CSRF > SQL Injection > XSS > SSRF > Database Migrations > Schema Versioning > Disaster Recovery > Backups > Failover > Multi-Region Deployments > Chaos Engineering > Cost Optimization > Cold Starts > Serverless Limits > Latency > Throughput > P99 Latency > Tail Latency > Network Partitions > Clock Skew > DNS > TCP vs UDP > HTTP/2 & HTTP/3 > gRPC > Webhooks > API Versioning > Semantic Versioning > Infrastructure as Code > Terraform > Helm Charts > Build Caching > Dependency Hell > Production Incidents > On-call > Postmortems ...until the app gets its first million users.
See More
jerrychaox
@jerrychaox
8 days ago
@kalasoo
agent A share session url, agent B read, humanity recap
jerrychaox
@jerrychaox
9 days ago
@_licgu
@labuladong_cn
怪不得 闷声不吭 特别奇怪🤣 现在过程都没法看了
jerrychaox
@jerrychaox
9 days ago
这几天深度使用loopx,多深度呢直接在codex轨迹盯着loopx的每个toolcall在干嘛,写了什么参数 为什么loopx是对的���有效的:感觉核心是记录了长程任务的语义状态,并且通过心跳等机制刷新agent的最新注意力,始终保持next token prediction在任务的正轨上 当然了任务质量仍然依赖你的Skill是否提供给Agent更好的任务拆解思路和认知 Agent不需要你定义 1 2 3 4…的相关步骤,后训练强化学习已经让agent能自己很好的推理和拆解轨迹了,如果死记硬背流程反而适得其反 Harness要做的就是给Agent更好的拆解思路Skill,tool,注意力反馈,LoopX我理解是让agent的对目标的推理始终保证在正轨上 Next Token Prediction Machine
See More
Ruiteng Huang
@huangruiteng
26 days ago
开源项目 LoopX:超长程 Agent 自主运行 200+ hours,状态不漂移。 我的技术主张是:LLM 上下文有限,长程 Agent 需要外置状态,通过完备的状态管理、监督和规划,让 Agent 无人干预时跑得稳、持续有产出;有人干预时跑得更好,能吸收反馈继续演进。 两条真实 trajectory 分别跨越 220.7 / 272.9 小时,跨多轮执行、等待、人工决策、writeback 与 resume 后,���个 loop 仍能找回目标、证据和下一步。 目前 LoopX 已有 3 个 showcase:auto PR issue fix、AutoML experiment 和 auto coredump fix。 以 OpenViking 开源仓库的 PR issue fix 为例,Agent 不只是循环写代码。它需要持续理解 issue 的不同状态,判断何时开发、何时等待、何时请求 review,处理 CI、冲突和上游变化,并连续交付多个 PR。 这对应 LoopX 的 domain state 管理:领域系统决定真实状态,LoopX 负责把状态投影成下一步可执行的工作。 与此同时,Agent 还可以在干活过程中实现能力自进化。当它发现现有系统缺少某项能力时,可以提出 feature、完成开发与验证、发布新的离线或在线版本,再使用新能力继续原来的任务。 长程 Agent 天然适合自进化,“完成工作”和“升级完成工作的系统”可以在同一条长程轨迹中发���。 LoopX 把这些信息外置成结构化控制面: • Goal / Vision:目标是什么,什么不能被局部优化牺牲 • Todo / Gate:当前执行的 frontier,以及必须留给人的关键判断 • Identity / Authority:谁能 claim、writeback、approve • Evidence / Receipt:每次推进留下什么可回读证据 • Quota / Scheduler:何时继续执行,何时安静等待 • Handoff / Recovery:换模型、换会话、换 host 后如何恢复 你也可以把它理解为一块专门给 Agent 设计的可执行 Kanban。 普通看板只展示“谁在做什么”;LoopX 的状态会直接约束和驱动下一次 bounded turn,让看板本身成为执行系统的一部分。 这套系统最强的地方是通用性。它不只可以修 PR,还可以做 auto research、长期实验、自媒体运营、复��� feature 开发和办公任务。 Agent 不再只是一次性的回答机器,而可以围绕一个人的 vision,长期工作、等待、吸收反馈、积累证据并持续演进。 LoopX 从一开始 build in public:状态协议、CLI、控制面实现和真实运行轨迹都进入了开源仓库;它也已经和 OpenViking、NoKV 等 agent infra 项目形成了开源合作伙伴关系。 我希望 LoopX 最终能放大每个人的 vision 和想象力。只要你有自己的目标、想法或技术主张,就能拥有一个全天候继续工作和探索的 Agent 系统,帮助你把愿景一点点变成现实。 欢迎试用、提 issue、贡献代码,或者用一个真实的 multi-day task 跑 LoopX。 https://t.co/ncHCZheYb7
See More
jerrychaox
@jerrychaox
9 days ago
@siddontang
manus是不是tidb
Last Seen Users on Sotwe
keit
Seen from
United Kingdom
#FlickOut Bullet
Seen from
Austria
АAV story
Seen from
Indonesia
Jacob
Seen from
Turkey
okan ÇAKAR
Seen from
Turkey
Arrrhhhh
Seen from
United States
MariahBrozゐ
Seen from
Indonesia
pecinta tante stw
Seen from
Japan
𓆩 리구 𓆪 riguruma 🪓 MV comms💖
Seen from
United States
The Thirst Is Real.
Seen from
United Arab Emirates
Trends for you
1
Warsh
Under 10K tweets
2
#MansBestFriendAwards
Under 10K tweets
3
PRIME Act
Under 10K tweets
4
#FursuitFriday
Under 10K tweets
5
#วาดฝันวันวิวาห์EP11
Under 10K tweets
6
Good Friday
Under 10K tweets
7
GAME DAY
Under 10K tweets
8
#LastFourWatched
Under 10K tweets
9
Donald Ducks
Under 10K tweets
10
Al Michaels
Under 10K tweets
Most Popular Users
1
Elon Musk
@elonmusk
241.5M followers
2
Barack Obama
@barackobama
119M followers
3
Cristiano Ronaldo
@cristiano
113.8M followers
4
Donald J. Trump
@realdonaldtrump
111.8M followers
5
Narendra Modi
@narendramodi
107.2M followers
6
Rihanna
@rihanna
98.6M followers
7
NASA
@nasa
92.4M followers
8
Justin Bieber
@justinbieber
91.7M followers
9
KATY PERRY
@katyperry
89.7M followers
10
Taylor Swift
@taylorswift13
83.6M followers
11
Lady Gaga
@ladygaga
75.1M followers
12
Virat Kohli
@imvkohli
72.8M followers
13
Kim Kardashian
@kimkardashian
70.7M followers
14
YouTube
@youtube
68.8M followers
15
Neymar Jr
@neymarjr
65.8M followers
16
Bill Gates
@billgates
64.9M followers
17
Selena Gomez
@selenagomez
62.7M followers
18
The Ellen Show
@theellenshow
62.3M followers
19
CNN
@cnn
61.8M followers
20
X
@x
60.7M followers
Olivia
Online
✨
⭐
💫