@ashfold

a small startup contributor. doing A.I. things and collaboration tools .

Shanghai
Joined October 2009
即使你只用gpt-6-sol干活/gpt-6-astra规划,200刀的GPT套餐实际用量只有Claude Pro的一倍左右。 再加上astra/sol的返工次数,我已经想退订了。
7
1
26
2,373
Keep your data safe is our mission. The team will continually expending our ZDR model list.
ZDR is now easier to spot in DimAgent. 🛡️ 14 models now carry a ZDR badge in the model picker. Prompts, files, and responses on these routes are discarded after each request—not retained by DimAgent or the model provider.
2
394
build dimagent for trust.
1
3
10
710
Han Cheng e/acc retweeted
让 Dim Agent 在后台跑几个比较重的goal,用 DeepSeek V4.1 Flash 持续反编译和分析一个程序。属于长时间不停读代码、执行命令、分析结果、继续修改的那种 Agent 工作流。 跑了两天,后台统计大概调用了 6000 多次,产生约 16 亿 Token,消耗了 8400 Credits。 整个套餐大概还剩6成左右。 考虑到官方还送了1个RESET点数,这70块钱花得值啊。
已严肃加入DimAgent!
9
2
1
24
6,708
我的想法是,既然不能阻止别人学,不如开始共享。🤤好歹不会再出现各种没有上下文的pr。
不管是喂给agent学习还是大模型训练,都能推进自进化😂
9
955
有这么个不成熟的想法。 以后其实没必要开源代码。 开源build时的session trajectory 可能更好。 更raw更底层。
把dlook这个tui文件阅读器扩展了视频,网页和图片的渲染能力。 整个binary只有8MB,非常适合在vps上用。 github.com/eric8810/dlook
4
2
8
3,056
把dlook这个tui文件阅读器扩展了视频,网页和图片的渲染能力。 整个binary只有8MB,非常适合在vps上用。 github.com/eric8810/dlook
1
1
9
1,982
唯一值得认真服务的是花真金白银买你服务的人。 唯一值得认真回报的是花真金白银服务于你的人。
1
25
1,019
Han Cheng e/acc retweeted
下午和夕阳针、小灰灰聊了两个小时,重温 DeepChat 的成长,也聊了我们在 Agent 时代的摸爬滚打,以及项目未来的方向。 模型在升级,我们也在努力给自己打补丁😂 和愿意动手、愿意分享的人一起折腾,挺开心。这场聊天收进了《为 AI 发电》第二期,欢迎收听,一起继续发电⚡️ xiaoyuzhoufm.com/episode/6ab…
3
5
13
1,608
😋😋😋可以多体验,有反馈就送reset
已严肃加入DimAgent!
2
1
9
1,291
✅cool!
我现在的开发方式... belike👇
4
790
大家是怎么看待开源但不开放,开放但不开源这个话题的?
8
21
2,503
🤣wc,别只是点赞啊,兄弟们
1
349
忘记说了, 现在最新beta版本的 dimcode 你可以 dim web 启动 web版来玩了. @DimAgentai npm i -g dimcode
3
3
8
759
So true
efficiency, productivity, speed we keep worshipping these words like they are what we live for ship faster merge more manage more agents compress every loop remove every pause turn every hour into output but what is the point of endless production if there is no time left to think deeply? not react not optimize not summarize not clear the queue think to sit with a question long enough that your real intention starts to appear to find the purpose underneath the motion to ask whether the thing being accelerated should exist at all ai could be a new canvas a way to make strange things personal things impossible things tools, worlds, poems, games, interfaces, films, languages, rituals things that let more people touch the shape of their own imagination but instead, so much of it is becoming slop factories more content more funnels more tickets more fake work pretending to be value you can merge 2000 prs you can manage 500 agents you can wake up to dashboards proving that the machine kept moving while you slept but what is the point if you only sleep 5 hours a day? what is the point if you stop talking to other humans? stop learning about the past? stop playing? stop wandering? stop being surprised? what is the point if your whole life becomes optimizing the system that is consuming you? speed is not meaning scale is not wisdom automation is not freedom if it only makes everyone run faster and where are we running? toward what? a world where every person becomes a manager of machines, and every machine produces more things no one had the time to truly want? the danger is not that ai makes us lazy the danger is that ai makes us endlessly busy that it gives us infinite production before we have found intention infinite execution before we have developed taste infinite motion before we have learned how to be still maybe the real frontier is not more speed maybe it is discernment knowing what not to make knowing when to stop knowing when the most productive thing is to sleep, read history, call a friend, play with a cat, walk without tracking it, or stare at the ceiling until the false urgency dissolves tools should give us more life not turn life into a tool if ai is going to matter, it should not just help us produce more it should help us become more human more imaginative more free otherwise, it’s the same old factory just without humans
4
975
Opus5.5太强了!找回了4.6的初心! 说话又好听,干活又利落,成本又不高。
1
19
1,021
Han Cheng e/acc retweeted
Introducing Contrastive Language Model (CLM): an ultra-fast System One Model trained with a contrastive learning objective that connects states and actions. CLM-8B is pre-trained on internet-scale data and delivers up to 9× faster inference than Jev ⚡ while achieving comparable performance across computer-use, gaming, and tool-calling tasks. With lightweight fine-tuning, CLM-8B sets a new SOTA on challenging agentic coding benchmarks, such as DeepSWE (81.6%) and Terminal-Bench 2.1 (87.6%). In contrast, Jev fails to serve as an effective verifier for these long-horizon tasks. We also build an efficient training and serving infra for CLMs by disaggregating states and actions, allowing their embeddings to be cached and reused independently. This substantially reduces inference latency in settings where the state evolves continuously while the action set remains fixed. Finally, we establish scaling laws for CLMs and show that the test contrastive loss decreases predictably as a power law in training compute, model size, and dataset size. 📄 Blog: contrastive-lm.notion.site 💻 Code: github.com/Contrastive-LM/CL… 🗣️ Discord: discord.gg/5dAQEDJBs 🤗 Data & Models: huggingface.co/Contrastive-L… More details on CLM’s architecture, data recipe, and scaling laws in the thread below 🧵
185
630
164
5,461
1,012,755