Tino Thamjarat (@V_TNO) header
Tino Thamjarat (@V_TNO) profile picture

I do stuffs with computer and mentoring programmers. Staff Machine Learning Engineer @unity Vector. Backing and advising: https://teapawt.org/t.co/43LFka55J2

Helsinki, Finland
Joined June 2010
Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)Photo by Tino Thamjarat (@V_TNO)
I built Qwenchana. Qwen 3.8 27b omakase serving setup for 2 x RTX 3090 It is working really well especially with 4-16 concurrent which is ideal for coding agent. I uses it to run it's own benchmark and fine tuning of the parameter afterward as well. github.com/vtno/Qwenchana
2
2
826
เชี่ย OpenCode Mobile App ของดีโคตร ๆ
1
98
Tino Thamjarat retweeted
Everyone seems to have forgotten that code is a liability, not an asset. That means that producing thousands of lines of code you didn’t read isn’t something to celebrate. It’s something to worry about! Every line of code needs to be tested, secured, and maintained. Even the ones that create no value for customers and therefore no value to the business. That’s why every line of code is a liability. And producing more liabilities isn’t good engineering or good business. Good engineering isn't about producing more code. It's about solving problems with the least amount of code. The asset is the solution, not the code.
154
278
39
2,127
61,897
Tino Thamjarat retweeted
Omarchy is now installing so fast on the fastest machines that we need two significant decimals to decide who goes faster. Here's your opening to beat the current install world record, @AnushElangovan! All you need is a 5.99s to claim the crown back 👑
112
48
16
1,469
61,646
Tino Thamjarat retweeted
the funniest outcome would be if the answer is... again, distinct apps with focused UIs for particular work + agents helping with that work. for example, I've tried managing email with all the assistant agents, but I can't make sense of the emails when everything comes in a text message format. I'd rather have a great email client that can show me emails when needed, but then there's a system + agent that handles stuff for me. Then again, if I want to search for something, I see an email, not a text message and a link. maybe even the AI/AI chat interfaces can't escape the fact that the best experiences are usually ones that are designed for something and for someone. Generalized tools and agents might not be able to provide that experience. then I think there is the group that just wants to automate their life fully but I still have emails that I actually want to read and respond to, not just have agents do it for me.
My current feeling is that frontier OAI/Ant/Gemini models with harness on desktop are phenomenally useful for real work... But despite how useful they are, I also still feel like my mind is being psychologically raided when I'm switching between all the different chat threads And on top of this, all of these agents I'm supposed to text all day that seemed awesome at first are in fact not very useful (dot/muse/instinct/whatever) Makes me increasingly convinced that "chat" alone is decidedly not the final interface of using a computer, or at least doing work on a computer. So much power and so little interface innovation Curious for those who disagree. Perhaps I'm just bad at this
84
19
13
622
56,482
Tino Thamjarat retweeted
The Unity CLI is officially out of beta with Version 1.0 and the Pipeline package 🎉 Using official Unity plugins for agents like Claude Code and Codex, agents can block out levels, write code, trigger compilation, fix errors, and playtest your scene.
35
34
4
448
27,794
Tino Thamjarat retweeted
Keeping human created art at the center of game building.
Unity acquires 3D asset creator Synty Studios; artist-created content to be integrated into AI game-creation platform Unity Spark gamesindustry.biz/unity-acqu…
3
9
87
3,765
Tino Thamjarat retweeted
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…
2,289
3,605
3,725
35,993
12,470,948
Tino Thamjarat retweeted
Qwen announces smaller Qwen4 models will be released soon! 🔥 Qwen4-27B will run on 16GB RAM setups.
📢 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. 👀
262
537
150
6,091
448,673
Tino Thamjarat retweeted
นึกถึงคลิปนี้ 555555 คนไทยชิลเกิ้นนน
กลายเป็นไวรัลในไต้หวัน! เมื่อนักท่องเที่ยวชาวไต้หวันเจอประสบการณ์สุดพีคกลางกรุงเทพฯ 🇹🇭🚖💨 ระหว่างรถติดหนัก คนขับแท็กซี่เกิดปวดท้องกะทันหัน เลยวิ่งลงไปเข้าห้องน้ำ แล้วบอกให้ผู้โดยสารช่วยย้ายมานั่งเบาะคนขับแทนหน้าตาเฉย 😂 ชาวเน็ตไต้หวันแห่คอมเมนต์แซวความชิลขั้นสุดของไทย: 🇹🇼 "นี่มัน GTA เวอร์ชันชีวิตจริงชัดๆ" 🇹🇼 "กล้าเอารถให้ต่างชาติขับต่อแบบชิลล์ๆ" 🇹🇼 "ยังไงก็ขับหนีไปไหนไม่ได้ เพราะกรุงเทพฯ รถติด!" สมกับเป็นเมืองแห่งความชิลล์และ Soft Power แบบไม่ปรุงแต่งจริงๆ 🤣 #AmazingThailand #ประเทศไทย #ไวรัล
6
1,939
5
2,279
148,712
Tino Thamjarat retweeted
we're worried about ai making some hyper logical decision that wipes humanity out but i'm more worried about the people working on AI having their heads so far up their ass they start to justify horrible things for "the greater good"
162
238
44
4,153
169,067
I just noticed that GPT models in OpenCode now have "flex" variants. That's nice. This is great for background task where I'm not in a hurry.
2
94
This is 🔥
AI interfaces nowadays are still pretty much turn-based. In my PhD thesis, I thought about what interaction would look like if we could go beyond taking turns. One example is intra-turn interaction:
2
158
This is something I've been on trial for a while and I think it's the best way to work with agents at the moment.
1
8
13
562
ยกเว้นฝั่ง tech ป่ะ ? 🤣
ฟันธงว่าอีกไม่นานคำว่า “ไม่ใช้AI” จะอยู่ในแคมเปญการตลาดทุกอัน
1
1
299
The agent framework I built for Vector does not allow dm'ing random ppl in the org. Only bringing public conversations to your own dm. I believe human communication must not be replaced by agent. It's weird and it's bad for the team.
2
3
152
Tino Thamjarat retweeted
I just finished talks about my software factories at two conferences. Afterwards a bunch of people came up and told me what they were surprised about. Here is a distillation of what people thought were hot takes from my two talks. First hot take: I tell everyone to slow down. Most speakers go on about how fast they're going, but I strongly believe in pacing AI outputs to human speeds. I regularly tell AI-pilled CIOs and CTOs to chill: almost nobody is _actually_ going fast with AI. Engineering still moves at engineering speeds, and business moves even slower. The ones pushing too hard are starting to see downtime for it. If you don't pace your AI to human speeds, everything starts breaking around you, even at small operations like my online video game. I only have about a dozen humans working with my factory, and only a few hundred active old-timer players in the community who get along well, and still, introducing AI has still been very rocky. My agents have, at times, overwhelmed my players with features, my accountant with emails, my merge queue with tickets, and my machines with load. Agents have pissed off my admins, resulting in name-calling, they've made messes in the game, and they've launched broken OSS without permission. The list goes on. I can get away with all this chaos because everyone involved in my operation is very forgiving. They're excited by the potential. But even so, I had to learn to slow down, real fast. And so that's what I preach. Hot take #2: Should you buy a software factory? Do you even need one? No. You probably don't need one. Factories take an extraordinary amount of upkeep. They turn into garbage mountains unless you put a frightening amount of time and tokens into curating them. I had to burn my previous five factories down since it eventually became cheaper to rewrite them than to fix them. So I'm not out there advocating for software factories or swarms just yet. If you do want one, be aware that it is a significant commitment of both money and human leadership to keep one running. Several people told me that I was the only one who stood up onstage, at either conference, and said Build, don't Buy. But my experience is that software factories grow to be highly bespoke to your domain. Mine is super tangled up with my game, and I think that's inevitable. Because the factory is not just building my product, it's supporting it too. It's a company in a box. And they're easy for Claude to build for you. Third and arguably hottest take: Next year will have a lot of human/agent and agent/agent office drama, resulting from bringing in AI employees, and it will be gloriously funny, but also frustrating. Many of you are already on this bandwagon, but everyone next year will have a personal chief-of-staff agent. Busy people, even hobbyists, will have whole entourages of helper agents. The hot take is that people will become so dependent on these little private entourages, that they'll bring them to work. Your people will talk to my people, etc. Whole protocols will emerge for private entourages negotiating work between humans, inside companies big and small. Nearly all humans will wind up having to start working with AI employees next year, and it'll be the beginning of the biggest cultural change we've seen in a hundred years. So that's the hot takes. Slow down. Only build a factory if you think you really need one. And focus on empowering yourself with your own agentic chief of staff (or team). Your entourage will define how you work with others, so start by perfecting how you work with them yourself.
193
320
106
2,928
343,202
Tino Thamjarat retweeted
Self-hosted Claude Managed Agents is now in private beta. You can host the agent harness, sandboxes, and session history, in your own cloud or on-premises, and choose where requests to Claude are sent.
431
884
408
15,043
1,457,530