Matoto πŸ… (@matotoLab) header
Matoto πŸ… (@matotoLab) profile picture

Trying AI tools. Sharing what works, what doesn’t, and what I learn. AI 도ꡬλ₯Ό 직접 써보고, λ§Œλ“€κ³ , 배운 것을 λ‚˜λˆ•λ‹ˆλ‹€. πŸ‡°πŸ‡·

Joined August 2021
Theo의 글을 μ½μ–΄λ³΄μ…¨μœΌλ©΄ ν•©λ‹ˆλ‹€. μ €λŠ” μ—”μ§€λ‹ˆμ–΄κ°€ μ•„λ‹™λ‹ˆλ‹€. GPTλ₯Ό 정말 μ’‹μ•„ν•˜κ³ , 일상과 μ—…λ¬΄μ—μ„œ 잘 써였던 일반 μ‚¬μš©μžμž…λ‹ˆλ‹€. κ·Έλž˜μ„œ 이 κΈ€μ˜ 기술적인 λ‚΄μš©μ„ μ „λΆ€ μ΄ν•΄ν•˜μ§€λŠ” λͺ»ν•©λ‹ˆλ‹€. ν•˜μ§€λ§Œ κ°€μž₯ 크게 κ³΅κ°ν•œ 뢀뢄은 λΆ„λͺ…ν•©λ‹ˆλ‹€. Opus 5.5λ₯Ό 더 μ„ ν˜Έν•˜κ²Œ λ˜λŠ” μ΄μœ κ°€ λ‹¨μˆœν•œ μ½”λ”© μ„±λŠ₯이 μ•„λ‹ˆλΌ, μ‚¬μš©μžμ˜ μ˜λ„λ₯Ό μ΄ν•΄ν•˜κ³  일을 λκΉŒμ§€ λ§ˆλ¬΄λ¦¬ν•˜λŠ” λŠ₯λ ₯μ΄λΌλŠ” μ μž…λ‹ˆλ‹€. 였늘 μƒ˜ μ•ŒνŠΈλ¨Όλ„ λͺ¨λΈμ΄ λ˜‘λ˜‘ν•œ 것과 λ³„κ°œλ‘œ, ν•¨κ»˜ 일할 λ•Œμ˜ μ‚¬μš©κ°μ€ 더 κ°œμ„ ν•΄μ•Ό ν•œλ‹€λŠ” μ·¨μ§€μ˜ 글을 μ˜¬λ ΈμŠ΅λ‹ˆλ‹€. μ € 같은 일반 μ‚¬μš©μžμ—κ²ŒλŠ” μ—μ΄μ „νŠΈκ°€ 일을 μž˜ν•˜λŠ” κ²ƒλ§ŒνΌ, 제 말을 μ΄ν•΄ν•˜κ³  μ œκ°€ μ›ν•˜λŠ” λ°©ν–₯으둜 μ›€μ§μ΄λŠ” 것이 μ€‘μš”ν•©λ‹ˆλ‹€. 무엇을 ν–ˆλŠ”μ§€ μ œκ°€ 이해할 수 있게 μ„€λͺ…ν•˜κ³ , μ œκ°€ νŒλ‹¨ν•  수 μ—†λŠ” λ‚΄λΆ€ 문제λ₯Ό λ‹€μ‹œ μ €μ—κ²Œ λ– λ„˜κΈ°μ§€ μ•ŠλŠ” κ²ƒκΉŒμ§€μš”. μš”μ¦˜ GPTλ₯Ό μ“°λ©° λŠλΌλŠ” κ°€μž₯ 큰 아쉬움은 μ„±λŠ₯이 μ•„λ‹™λ‹ˆλ‹€. μ„±λŠ₯이 λ’€μ²˜μ§„λ‹€κ³  μƒκ°ν•˜μ§€λ„ μ•ŠμŠ΅λ‹ˆλ‹€. μ†Œν†΅μ˜ λ¬Έμ œμž…λ‹ˆλ‹€. λ˜‘λ˜‘ν•˜λ‹€λŠ” 감탄보닀, β€˜λ‚΄ μ˜λ„λ₯Ό μ•Œμ•„λ“£κ³  ν•¨κ»˜ 일을 λλƒˆλ‹€β€™λŠ” κ²½ν—˜μ„ 더 자주 ν•˜κ³  μ‹ΆμŠ΅λ‹ˆλ‹€.
30
Ferroflora A 16-second procedural sculpture made in Codex (6.2 Sol, creator-reported). The gold sphere represents a magnet. As it moves, the spiked metal folds into petals, then closes again.
2
2
100
Last month, I shared a diagram imagining dot coordinating different tasks. Connecting multiple local computers was below the dashed line back then. Now it is a real feature. Being able to choose the computer for each task is a step in the direction I had hoped for. I’ve updated the diagram to reflect that. What I’m curious about now is whether it can accurately track progress across tasks, check the results, and keep the work moving through to completion.
πŸ€– Made with AI
You can now connect multiple local computers to the same dot and choose which one it uses for a task. It can build and test your app on a dedicated machine while you keep coding on your laptop.
2
57
6.2 Sol이닀!!! γ€ˆTide Relay〉 μƒˆλ²½ λ°”λ‹€μ˜ 무인 κ΄€μΈ‘μ†Œκ°€ κΉ¨μ–΄λ‚˜λŠ” 18초짜리 3D μ• λ‹ˆλ©”μ΄μ…˜. νŒŒλ„μ™€ λ°˜μ‚¬, 카메라, 해무λ₯Ό κ°€λ₯΄λŠ” νƒμ‘°λ“±κΉŒμ§€ μ½”λ“œλ‘œ λ§Œλ“€μ—ˆλ‹€.
1
1
185
6.2sol 도착이야!!! μ œκ°€ Three.js둜 λ§Œλ“  κ±Έμ–΄ λ‹€λ‹ˆλŠ” κ±°λŒ€ μ„±μž…λ‹ˆλ‹€. μ—¬μ„― λ‹€λ¦¬λ‘œ μ•ˆκ°œ λ‚€ 골짜기λ₯Ό κ±΄λ„™λ‹ˆλ‹€.
1
2
234
6.2sol 도착이야!!! μ œκ°€ Three.js둜 λ§Œλ“  λ‘”ν™© μ„κ΅΄μ˜ λ°€μž…λ‹ˆλ‹€. 천μž₯ λ²½ν™” 속 λΉ„μ²œμ΄ κΉ¨μ–΄λ‚˜ λΆλ‘μΉ μ„±μœΌλ‘œ μ΄μ–΄μ§‘λ‹ˆλ‹€.
1
1
171
6.2sol 도착이야!!! μ œκ°€ Three.js둜 λ§Œλ“  λ²„μ „μž…λ‹ˆλ‹€. 펠리컨이 일식 μ•žμ—μ„œ μžμ „κ±°λ‘œ 루프λ₯Ό λ•λ‹ˆλ‹€.
1
84
6.2 Sol has arrived! After all light has faded, only time remembers the last glimmer. The End of Time β€” an interactive Three.js artwork that lets you rewind time. I made this in 8 minutes and 30 seconds using the exact prompt I saw in another post. Prompt in the replies.
1
83
I use dot as an AI middle manager. 1. Local Codex and dot work on their own computers. 2. Progress and remaining tasks go into Space. 3. My dot, Mato, reads it and tells me where things stand and what's next. Space is the shared workspace connecting local and cloud work. Having it right inside ChatGPT makes it easy to connect everything. Some parts are still rough, but I hope they keep getting smoother. And seriously, when is Astra coming out?
πŸ€– Made with AI
Pro tip: just send the link to this article directly to your dot and it'll create a responsibilities page for you Then go into that Page and delete the ones you don't want, and ask dot to add the ones you do want
86
Let’s get all our ChatGPT complaints out here πŸ˜‚
hi all, two things: 1. usage limits are back to being double – your feedback worked 2. we today kicked off an intense sprint to dramatically improve the app simplicity and performance. i will oversee this. more to come. now, send me your complaints
6
212
Working with AI has made me want to build a loop that carries lessons into the next task, rather than stopping at one result: review the output, turn feedback into instructions or skills, then check whether it helps on the next task. The parts I keep thinking about are steps 4 and 5. How much can we trust AI to decide what a good result looks like, spot what’s missing, and give useful feedback? I suspect there’s still a lot that needs human judgment in many kinds of work. I haven’t tried this across lots of fields, though, so I’d like to explore how far I can take it in my own work first. If agents eventually become reliable at this kind of judgment and feedback across different fields, could that be a step closer to AGI? What does this look like in your work? Have you managed to automate much of the loop, or are there parts you still need to review yourself? I’m curious about both what works today and what might become possible.
πŸ€– Made with AI
1
3
234