JΞNSΞN (@jensenloke) header
JΞNSΞN (@jensenloke) profile picture

running my agent army every day. 🇸🇬 ai and agentic coding enthusiast. https://teapawt.net/t.co/pr2G4C2P7J founder, @QwenDevs and @DevinAI ambassador

Singapore
Joined November 2010
Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)Photo by JΞNSΞN (@jensenloke)
Google - RSI achieved?
What is happening??? Google releasing models like CRAZY
1
43
Bought this as my taobao stash after seeing @thdxr’s post and my friend who travelled with me to Guang zhou used it! Works like magic!
43
Here we go @NathanTee3
Phew, ChatGPT for Accounting is now available. Our new Accounting plugin and partner plugins help you close your books with less manual work for tasks like: - Month-end reports - Bank reconciliation - Data entry - Audit prep Put ChatGPT to work with tools like @QuickBooks, @Xero, Oracle @NetSuite , @BILLcom, @FreshBooks, @RilletHQ, and @Meet_campfire. Try it here: openai.com/business/solution…
1
64
In the age of autonomous agents and objective driven agent deployments - I see us moving toward “policy engineering” instead of context or prompt engineering. In policy engineering - you write the policies for behavior of agents you deem acceptable, and in the same manner you write policies that discourage agent behaviors, and agents following policies know what boundaries they have to execute and what to ask for human approvals. Tests, adversarial reviewers start to feel more and more like enforcement agencies - keeping agents that are non compliant in check! More and more human society like?
3
1
176
My second AI device from taobao! An ESP32-S3 amoled display with battery! Gonna have lots of fun with hardware infused with AI when I’m back in SG!
1
1
93
Very excited about linking @NousResearch’s Hermes to this!
2
145
I’m on holiday! But here’s the new drop by @QwenDevs! Will test more when I’m back this weekend!
📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery! Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window. Highlights: - Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation. - Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables. - Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery. - $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%. The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder. Start building today! 🚀 - Blog: qwen.ai/blog?id=qwen4-max - API: qwencloud.com/models/qwen4-m… - Token Plan: qwencloud.com/pricing/token-… More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀
1
1
122
Relentless. This is the way to go. Execute and then think. Iterate. Rinse and repeat and be stronger than ever.
i learnt this lesson this year. it's helped me follow through on my ideas and not get stuck overthinking it don't ask if you should do the thing. do it, then come back with a demo or something tangible you can just do things
81
This is huge!
HUGE NEWS! and Huge W ! It's official! Guys, if you love @DevinAI and you love SWE-2, you are winning right now. @cognition decided to make SWE-2 FREE for all Pro, Max, Team plan users No more promo extensions, it's just free, that's it. Forever. Devin is the only plan that gives you absolutely free tokens of a high class model like SWE-2 This makes Devin Pro 20 usd plan the best value plan just like that!
2
146
Coding on the aeroplane? 🤣 @CSAIRGlobal
2
6
219
If this solves role based access controls.. it will be lit for enterprises
Vibe coding for enterprise never quite took off. Who wants to figure out all the security and hosting complexities? But what if we took care of this using Devin’s compute stack? We’d make it so apps could only be accessed by your org, and access controls to data would be shared via the access Devin already has So introducing Devin Apps, we made sharing internal tools and apps viable, and spin down apps when they are not in use
52
So yesterday we broke a personal high. i debugged 6 agent tickets last night used by my team at Success IT. my main job now is to help my team debug our autonomous agents so we can run faster. 4 @openclaw issues, 2 @DevinAI workflow bugs. Loving the new paradigm.
1
71
totally agree. the concept is right. what happens after is managers may want to stop talking to some people, as they are results oriented.
i found "executive mindset" to be the biggest differentiator from people who can use agents super effectively it comes natural for people who had been an executive of a large org before, but it's counter-intuitive for people who haven't done so a few examples 1. after you send a prompt, do you stare at the chat to see what the agent is doing? most agent UX today leads people to do that, but a good executive never watches over an employee's shoulder after they've sent an ask - they are immediately on to the next problem 2. do you rely on chat for important decision making? "just chat" sounds elegant, but there's a reason company executives rarely rely on plain talking for high stake decisions instead, they ask the team for documents or presentations. it puts a bit more prep work on the team, but the discussions end up being a lot more efficient 3. when your agent did something wrong, do you curse at it and twist its arms to do it right? some successful executives actually do that as well, but they also do something else afterwards - figure out what allowed the mistake to happen in the first place, and stop it at its root 4. do you spend all your time carefully examining everything to make sure the code is bug free? now this is getting spicy, but you can pick any popular product on earth and you won't find a single one that's bug free good executives accept the calculated risk and invest time in the right workflows to catch bugs early before shipping, get alerts if they happen, and making sure fixes can go out quickly - never make themselves the bottleneck by being the tester our tools, skills, workflows etc change all the time, but building the right mindset is durable and can help you for a long time if you aren't clear how to acquire the mindset yet, i recommend starting with asking yourself this when you try to decide to do something or not - "if i have 100x more agents doing 100x more work for me every day, how would i do this?" do this enough times, and you'll find yourself actually able to control 100x more agents effectively
74
This was one hella awesome event by @yongquanYQ and the rest of the crew @FanAun @DevinAI!
Replying to @yongquanYQ
7/ all in all was a very cute event with technical demos and great convos on where we're headed! thanks to the goat @brianchew for the lovely xt100vi lol i need to dabble into better cameras/iphone soon do check out the devin ambassadors @jensenloke and @kellyann3644 who are doing their own cool stuff in the space! thanks everyone for coming!
5
175
JΞNSΞN retweeted
Ain’t nothing cuter than a @DevinAI meetup 🇸🇬
2
1
24
757
Am going to release a special video later for my @DevinAI @devindevelopers workflow!
62
This is super cool af! Man I should try something like this with vector!
I got a 1.9B model to watch a restaurant camera and tell staff which tables need cleaning 🍽️ It runs on my laptop. No cloud, and it generates zero tokens. Built over a weekend with @liquidai d1-2B
1
3
338