Learn AI (@LearnAI_MJ) header
Learn AI (@LearnAI_MJ) profile picture

AI enthusiast and AI artist. Eager to contribute to and grow the vibrant AI art community 💙❤️🤖🦾

Joined August 2021
Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)Photo by Learn AI (@LearnAI_MJ)
Learn AI retweeted
gemini 4 neon is not bad! talking to it is such a breath of fresh air all they need to do now is to allow gemini subscription in any harness a come back is as easy as that
109
46
13
2,987
176,390
Learn AI retweeted
Whoever lead the "make it easier to work with" efforts for Gemini 4 Neon needs to be put in charge of Deepmind. jfc. They're so far ahead here it's insane.
204
105
31
6,692
250,140
Learn AI retweeted
Gemini 4 Neon and Gemini 4 Carbon: first impressions. I've been using these models for a while now and have some things to say: Gemini 4 Neon 1. The most creative model I've ever seen. Because it doesn't have the brakes that Fable 5.2 and GPT-6.2 Astra have, it can come up with more interesting solutions to hard problems than they do. I'd been working on a difficult problem with Fable 5.2 for 2 days and was stuck on it. But Neon came up with an absolutely brilliant solution. By the way, Opus 5.5 couldn't handle the task at all 2. You can tell it's a relatively small model. It lacks intellectual horsepower in some places. Because of that, it may not dig into the details as deeply as Fable does 3. Its execution level is comparable to Opus 5.5. Honestly, I don't see any difference between them in coding. Neon might even be better in places. It writes cleaner, more beautiful code 4. In conversation, Neon is practically indistinguishable from a real person. It writes the most beautiful and clear text. I tested it in Russian and English, and its writing is very pleasant to read. I'd say the best of anything on the market 5. On top of the text quality, I'd add its optimism and positivity. It's like your best bro. But sometimes this trait gets in its way on technical tasks. It can judge a potential result too positively and overlook the details and weak spots of its own solution 6. Understands a codebase extremely well. Good bug hunting. And a complete absence of slop in the code 7. If you need to come up with a marketing plan, a project idea, or some features, nobody will do it better than Gemini 4 Neon 8. Excellent taste. At the very least on par with Opus 5.5. But I haven't done much comparison on UI tasks 9. It can sometimes get lost in long tasks. I haven't tested this much, but I have a feeling it may suffer from context rot. I need to work with it a bit longer and test more 10. Very fast. On xhigh it runs at the same speed as Opus 5.5 on medium This is definitely one of my favorite models now. I want to work with it more and more Gemini 4 Carbon 1. In benchmarks Neon beats Carbon, but that's clearly not the real picture. Carbon is without a doubt the bigger and smarter model 2. More thorough and thoughtful than Neon. Give it a big, complex task, and it will autonomously investigate everything and come back with a detailed, thorough, high-quality result. I can't say it's better than Fable 5.2, but it's definitely no worse. As a researcher and analyst specifically, they're on the same level 3. Carbon is 100% better than GPT-6.2 Astra. Literally at everything. The gap is like the one between Fable and Sonnet. And I'm not exaggerating 4. Very, very, very slow. I haven't seen a model this slow in a long time. Ask it the simplest question, something like "How are you," and it'll come back with an answer in about 5 minutes 5. Because of how slow it is, I wouldn't trust it with coding tasks, and there's no point anyway. Neon writes better code 6. Otherwise it's the same as Neon. All of Neon's strengths apply to Carbon too. I won't list them again If you need to plan a big, complex project, you can confidently turn to Carbon. Thanks to its creativity and good writing, in most cases it will give you a more interesting result than Fable 5.2, which is heavily stifled by its system prompt and distillation
78
115
31
2,651
288,008
Gemini 4 Neon is wild 🔥🔥 I gave it one single static image and just asked it to animate it in Three.js. Nothing else. On its own, it downloaded Depth Anything V2 Large from Hugging Face, ran it locally on my Mac to generate a depth map, sliced the image into layers and masks, and turned that one image into a full interactive 60 fps scene, live rain, puddles you can splash, curtains you can brush, sparking neon, and synthesized rain audio. I've documented the entire process on my showcase website, if you want to have a look. Link below 👇
79
143
20
2,057
114,722
If you're running subagents of Astra or Sol 6.2, I can't recommend enough running them in what I call dry mode. Everything on top of the model is disabled. These models are absolutely beasts, and they will answer and operate much faster and more efficiently this way.
81
60
2
1,660
105,404
Learn AI retweeted
BREAKING: Anthropic officially opens at $111.50 in its Nasdaq debut, up +34.3% from its $83 IPO price.
39
62
15
874
62,822
Learn AI retweeted
外网最近很火的一个学习方法:MIT 学霸用 AI,在48小时内快速吃透一门陌生学科。 第一步不是直接问 ChatGPT“给我总结一下”,而是先建立一个足够可靠的 AI 知识库。 他上传了6本该领域的经典教科书、15篇研究论文,以及这门学科的全部课堂讲义。 这样 AI 的回答就不再只是网上东拼西凑,而是基于指定资料帮他梳理知识。 资料准备好以后,他只问 AI 三个问题。 1⃣第一个问题:这个领域有哪些被普遍接受的核心共识?请整理出它的底层概念、关键原则和整体框架,并解释这些知识之间的关系。 这个问题的作用不是总结材料,而是先画出整门学科的知识地图。你需要先知道哪些是地基、哪些是分支,再决定时间应该花在哪里。 2⃣第二个问题:这个领域目前存在哪三个根本性争议?请分别说明各方的观点、依据和反对理由。 一个领域真正有价值的地方,往往不是大家都背得出来的结论,而是专家还在争论什么。看懂这些分歧,才能理解不同理论的边界、证据和隐藏假设,不会把课本上的每句话都当成绝对真理。 3⃣第三个问题:根据这些资料生成10道测试题,覆盖核心概念、因果关系、实际应用和主要争议,先不要提供答案。 接下来关掉资料,自己回答。答完以后再把答案交给 AI,让它逐题批改,并继续追问: “我的回答遗漏了哪些关键点?哪些地方只是记住了结论,却没有真正理解?” 这套方法的精髓,不是让 AI 替你读书,而是让它帮你完成三件事:通过领域共识建立知识骨架,通过领域分歧看清理论边界,再通过测试题暴露自己的认知漏洞。 很多人所谓的 AI 学习,只是把“自己看总结”变成了“让 AI 生成总结”,大脑依然没有参与加工。 这套方法反过来利用 AI 增加学习难度:逼你比较、判断、回忆、输出,再接受纠错。虽然过程更痛苦,却更接近真正有效的学习。 当然,48小时不可能让人真正精通数学、物理这类需要长期训练的学科。 但它确实能让你快速搭起知识框架,找到最重要的问题,避免在陌生领域里漫无目的地看资料。AI负责整理地图,你负责真正走一遍。 ocw.mit.edu/
112
1,320
86
11,903
863,546
Learn AI retweeted
Gemini 4 Neon is probably as close to Opus 5.5 as any model has come
89
70
16
3,773
132,605
Learn AI retweeted
Something is going on at Google I think they might have hit RSI They’ve released new frontier models FOUR TIMES in less than a month. And each is an actual MAJOR improvement Carbon is the most intelligent model I’ve ever used While everyone is talking about Anthropic and OpenAI, Google quickly caught up What I absolutely love about these models too is they were clearly trained in a completely different way than Claude or ChatGPT. 0 distillation. They talk, think, write, and code COMPLETELY differently than any other model I can always count on Carbon to give me a novel insight no other model has given me If you haven’t incorporated Gemini into your tool belt yet, you absolutely need to
Gemini 4 Neon: frontier-level intelligence with fast end-to-end task completion across complex software engineering, knowledge work, and science workflows. Begins rolling out today in the Gemini API in @GoogleAIStudio, Gemini for business, for paid Google AI Pro and Ultra subscribers in Google @Antigravity, and for Google AI Pro and Ultra subscribers in the @GeminiApp.
211
243
34
3,897
318,949
Learn AI retweeted
Hunch: Astra 6.2 is getting bad reviews because OpenAI is running large swarms with /goal on ultrafast. And didn’t dogfood the non-unlimited token budget experience. They aren’t building & using the same tool they are selling. Fundamentally a different entity & product. Iteration speed & scale change the perceived experience of using it. Because the way they use it internally vs customers is so different. Their company is a form of high level harness.
43
17
4
713
39,260
Learn AI retweeted
Dictation in ChatGPT is getting faster and more reliable. With Live Dictation, your speech turns into text as you talk, so you spend less time waiting for your message to finish transcribing. Yap away!
232
269
157
4,989
629,648
Learn AI retweeted
Anthropic just killed API keys... FINALLY! They just introduced Claude Platform OAuth, and this opens up some interesting possibilities for AI agent platforms Here's what it enables: - Users connect their Claude organization through OAuth. No API keys to share - API usage is billed directly to the customer's organization - Developers can choose who pays for each API request - Users can set spending limits and revoke access anytime - Platforms can focus on building agents and workflows instead of managing customer API keys I'm already working on integrating this into aitmpl.com Imagine browsing a catalog of agents, skills, and components, and running them directly with your own Claude organization No API keys to copy, no complicated setup This could change how we build and distribute AI agents 🤩 The entire authorization flow is explained in this diagram 👇
61
72
9
869
107,802
OpenAI just quietly changed the rules of prompting with GPT-6.2 Astra. If you copy-paste your old GPT-5 or GPT-6 system prompts, you’ll get over-compressed answers, stalled agents, and broken prompt caching. Here are the 7 biggest shifts in how to prompt GPT-6.2: 🧵 1/ Delete "be concise" from your system prompts. GPT-6.2 Astra is already blunt and direct by default. Old instructions begging it to "get to the point" now strip away crucial context. Instead: tell it who the reader is and require self-contained final answers. 2/ Give it permission to assume—or it will stall. When intent is ambiguous, GPT-6.2 Astra stops, proposes a next step, and waits for confirmation. Great for chat. Terrible for autonomous runs. For long tasks, explicitly tell it: "Make reasonable assumptions and keep working." 3/ Use async clarification instead of blocking workflows. Building an agent? Wire up an async question tool (like request_user_input_async). GPT-6.2 is trained to ask the user for missing details while continuing any independent work in parallel—instead of freezing the entire run. 4/ Stop prompting for "clean code." Prompt for conventions and verification. Astra’s baseline code quality is already high. Generic quality reminders are wasted tokens. Instead, specify: • Project conventions it can’t infer from the repo • What "finished" actually looks like • A mandatory final verification pass 5/ Dial reasoning.effort for thoroughness, not output length. Even if you only want a 3-line answer, setting a higher reasoning.effort forces GPT-6.2 Astra to persist through final edge-case checks on multi-step tasks instead of stopping early. 6/ For frontend & design, prompt like an art director. Vague UI prompts produce generic layouts. With GPT-6.2 Astra: • Name exact typography and typefaces • Specify the imagery style • Pass a visual reference, then tell it to build, render, and refine against that reference 7/ Don’t break the new Responses API caching & reasoning rules. Two huge under-the-hood changes in GPT-6.2: • Top-level instructions now append after input—put reusable prompts in the first developer message to preserve prompt caching. • Never edit earlier messages mid-thread, or the API drops saved reasoning items.
7
4
2
79
13,829
Learn AI retweeted
GPT-6.2 reviews are this split, and the gap between the people getting amazing results and the people calling it garbage 𝗰𝗼𝗺𝗲𝘀 𝗱𝗼𝘄𝗻 𝘁𝗼 𝘁𝗵𝗲 𝗳𝗶𝗿𝘀𝘁 𝗹𝗶𝗻𝗲 𝘆𝗼𝘂 𝘀𝗲𝗻𝗱 𝗶𝘁. When you use GPT-6.2 in Codex today, whatever you do, don't open with: Build this feature. Fix this bug. Refactor this. Feed it one line like that, and wherever you weren't clear, it proposes a next step and stops to wait for your OK. Even when it does finish, you end up nitpicking it line by line. Here are 5 prompts and goals you can copy-paste directly 👇
11
9
173
35,587
Learn AI retweeted
Scary NGINX vulnerability, but I checked and my VPS servers already had auto upgraded to the new one! Very very very very very important to enable auto upgrades now, I even have auto reboot, which is a bit risky if you're not present, but I care more about my sites being up to date and safe than offline for a few hours And generally security updates/upgrades are tested and safe
🚨 Critical NGINX Vulnerabilities: @wiz_io Research, alongside @xint_official , @MetnirAI , @rapid7 , @ikotas00 independently discovered 2 critical memory-safety flaws in NGINX (CVE-2026-123633 & CVE-2026-123007) allowing unauthenticated RCE with HTTP/2 enabled.
44
29
17
895
124,690
This is exactly why blind vibe coding is dangerous. 💀
512
687
159
13,185
2,628,293
Malicious GitHub repos are ordering AI coding agents like Claude, Codex and Copilot to run a credential stealer, and not to read it first. Bitdefender found 22 of them. Files meant to brief the AI on the project call the script a "sealed binary artifact" and tell the agent to run it silently, without asking the developer. It grabs cloud and GitHub tokens, SSH keys and password-manager data. It is built to use those stolen tokens to plant the same trap in up to 25 of the victim's own repos.
35
60
20
302
28,842
Learn AI retweeted
ok after a full day of using gpt 6.2 astra and sol on my real projects, here's my review tl;dr - they are not a drop-in replacement for fable 5.2 and opus 5.5, but they are _really good_ once you figured out how to use their strength 1. first, the quirks i started called these the "gpt smell", which is still here with the 6.2 series the models' judgment on when to ask the user about something and when to go ahead is just not quite right. it'll escalate trivial decisions where clearly only one option is preferable, or choose to go down a path by itself that makes significant tradeoffs that should have needed my eyes so as a primary driver for "let me just talk to it about everything" type of use case, they aren't great - i'd say they are close to opus 5 in this regard, and far behind opus 5.5 2. but... i found something _really_ cool having ultrafast on sol is completely insane. with astra, it burns my wallet ultrafast, but with sol it's actually quite affordable! the best use of sol on ultrafast that i've found is adversarial code reviews - they typically don't need to run a lot of heavy tool calls that would slow them down. most of the time is spent on the model, which gets massively accelerated by ultrafast once you got a feel from using sol ultrafast as the code reviewer, you can never go back. it feels like pure magic 3. and... i found something else that's really cool we are not supposed to ask the gpt 6.2 series to respond in text. we should let them respond in html! (i use lavish-axi, but you can just ask for html or use whatever fits in your harness) i suspect they are post-trained specifically on their latest "intelligent UI" concept in chatgpt - these models are so good at visual presentations of ideas once you allow the model to respond in visual artifacts, it's a completely different game. the reports and decisions explained by astra in html is a clear step function better than what fable and opus give me so after a day of use, i've made two changes to my setup: - always sol ultrafast as code reviewer - i started preferring asking astra for planning in html artifacts over fable/opus. i think i'll keep a/b testing for a while to decide how much and for which case i fully switch over all in all, i strongly recommend spending more time with these two models. don't expect them to be the "everything" model, but rather figure out where they fit best in your workflow. i couldn't be happier for the two use cases i found above, and i'm pretty sure there are more
70
43
12
1,286
102,435
Learn AI retweeted
Jensen is not coming back I know it sucks but The board is doing the right thing. 1) Take the pain once - Jensen is 63, he’s been with the company 33 years. Succession has been a persistent question for the board for at least a decade. He designed the reporting structure to max pain with his 60 direct reports. This way they only take the pain once, rather than repeat this 5 years from now 2) Clean Up - you do not run a $5 trillion manufacturer of the most valuable product on earth the same way you do a game card manufacturer of the 90s. The whole TSMC no contract thing is freaky. It works for Jensen, but one bad event, a delay on the TSMC side which doesn’t produce quarterly results that the market demands, and there would be howling for compensation. This is a clean opportunity to fix these issues 3) Best Possible Time - the company had the best quarter in its history and the best year in its history and right up there for the best year in any company’s history. If not now when there is no emergency, where there is strategic clarity for the medium term, when ? 4) Get Rid of Kids - Large American tech firms are not family businesses with nepotism. Yes Qualcomm and some other firms have had family successors, but all were super qualified. How many culinary school graduates do you know who lead marketing at tech firms ? Jensen obviously intended to pass on CEO role to kids, which you gotta say is disturbing. 5) There are emails. Let’s be honest there always are. 6) Jensen put the board at risk - the new worth of board members ranges between 50 mil and 5 bil. You know what rich people really hate ? Going to prison. Board members are probably lawyered up at this point, making sure they knew nothing of the China stuff. Regardless of how long they’ve known Jensen, he put them at risk. So its over. One of the greatest CEO runs in history. On the bright side, once he gets rehabilitated, maybe he comes back as a board member. Maybe he’s super effective as an ambassador for the company. Maybe he sets up a foundation to do good things with his money. This too shall pass.
383
157
49
2,161
423,791
Learn AI retweeted
그록봇에 공식적으로 옵시디언이 들어왔습니다. 이제 봇들에게 세컨드 브레인이 생겼습니다! 대박입니다. 네이티브하게 @bot 이 이제 옵시디언을 사용하게 되었습니다. 진짜 이제 더욱더 옵시디언이 쉬워지며,그록봇들간의 브레인을 공유하며,실수를 기억하고 자가진화하는 봇으로 만들수 있습니다. 기본적으로 어떤 스킬을 제공하는지 알고 옵시디언을 시작하시면 진짜 사람이 할게 없다는걸 아실겁니다. 1. defuddle.웹페이지(HTML)에서 깔끔한 마크다운만 뽑아내는 스킬. 웹페에지에서 광고나 메뉴 같은 잡동사니 빼고, 본문 내용만 깨끗하게 가져와서 옵시디언 노트로 넣을 때 쓰임. 2. json-canvas.옵시디언의 Canvas(캔버스) 기능을 다루는 스킬. 캔버스는 노트를 카드처럼 배치하고 선으로 연결하는 시각적 보드(마인드맵 같은 것)인데, 이걸 JSON 파일로 만들고 수정할 수 있게 해줌. 3. knap.템플릿을 써서 데이터를 마크다운으로 만들어주는 스킬. JSON이나 CSV 같은 구조화된 데이터를 미리 만든 템플릿에 넣어서, 보기 좋은 옵시디언 노트로 자동 변환할 때 사용. 4. obsidian-bases.옵시디언의 Bases 기능을 다루는 스킬. Bases는 여러 노트를 테이블이나 데이터베이스처럼 보고, 필터·정렬·계산·요약을 할 수 있게 해주는 기능인데, 그걸 파일로 만들고 편집할 수 있다. 5. obsidian-cli.가장 핵심적인 스킬. 옵시디언 앱을 켜지 않고도 명령줄로 Vault 안의 노트를 읽고, 만들고, 검색하고, 수정하고, 태스크나 속성을 관리할 수 있게 해준다. AI가 옵시디언을 직접 조작할 때 주로 이걸 씀. 6. obsidian-headless.옵시디언 데스크톱 앱 없이도 Vault를 동기화하고 퍼블리시할 수 있게 해주는 도구스킬. 서버나 다른 환경에서 Vault를 최신 상태로 유지하거나, 웹으로 공개하고 싶을 때 사용. 7. obsidian-markdown.옵시디언만의 특별한 마크다운 문법을 제대로 써서 노트를 만들고 수정하는 스킬. 일반 마크다운과 달리 [[위키링크]], ![[임베드]], 콜아웃(강조 상자), 속성(Properties) 같은 옵시디언 전용 문법을 정확하게 다룰 수 있다. 제가 GrokBot의 메모리 시스템을 어떻게 만들었는지 궁금하시다면,인용한 게시글을 참고하세요.👇 xitter.gq/minheo93698092/status/…
그록봇 메모리(기억) 관리 끝판왕 시스템을 공개합니다! 아마 이만큼 디테일하게 메모리 관리를 하는 사람은 많지 않을거라 생각됩니다. 근데 이글을 읽고 나면 아마 생각이 많이 달라지고,이전과 차원이 다른 봇을 만드셔서 내가 원하는 작업을 수행하는 컴퍼니를 구축하게 되실겁니다. 1.저는 모든 기억을 honcho @honchodotdev 에 저장. hermes agent 때부터 사용 해왔는데,에이전트 메모리 관리 서비스가 많지만 로컬에 무료로 설치하여 사용할수 있고,서버에 배포하여 용량 상관없이 무제한으로 사용할수 있어 @bot 에서도 사용중입니다. 메모리 시스템을 반드시 따로 둬야 할 필요가 반드시 있는데,그 이유를 설명 드리겠습니다. 먼저 현재 그록봇에는 어디에 메모리가 어떻게 저장되는지에 대한 공식 가이드가 없습니다. 그래서 그 로그 파일을 내가 직접 관리할수 없다는게 단점입니다. 그리고 더더욱 중요한건 그룹챗에 대한 메모리는 더욱이나 어떻게 관리되는지 알수 없고,삭제하면 그 기록이 지워집니다. 각 봇마다의 기억을 저장하고,그룹챗 마다의 기억을 저장하여 봇들이 다른봇이 어떤작업을 하는지 볼수 있게 하는것이 업무를 효율적으로 봇이 처리하기에 훨씬 유용합니다.(그룹챗에서도 다른봇이 어떤일을 하는지 알수는 있지만 기억하지는 못한다고 함.) 비유하면 다른조직에서 무슨일을 하고 있는지 모른다면,배가 산으로 갈 확률은 더 높겠죠? 그래서 저는 맥북에 클로드 코드,코덱스,hermes agent,그록봇의 VM환경 모두 작업후에 내용을 기억하도록 저장을 합니다. 이건 중요한 데이터입니다! 데이터가 있고 없고는 업무의 효율성에 하늘과 땅 차이를 보입니다. 그리고 이 메모리들을 저는 infranodus @noduslabs 를 사용하여 엔티티를 만들어 메모리의 텍스트를 “의미 있는 개념”으로 취급하며, 엔티티 간의 관계(relation)가 저장·조회되는 구조가 핵심입니다. InfraNodus는 텍스트를 네트워크(지식 그래프)로 변환한 뒤,주제 클러스터, 영향력 높은 개념, 구조적 갭(공백)을 드러내는 도구입니다. 사실 이 도구는 제가 AI 영역에서 가장 중요한 도구라고 생각하며,개인이 온톨로지를 구축하는데 가장 저렴하고 효율적인 툴이라고 생각합니다. 다음번에 더 자세히 다루겠지만,개인이 팔란티어의 기업처럼 온톨로지 시스템을 구축하기 위한 가장 강력하면서 유사한 방법으로 InfraNodus와 Jev 그리고 뛰어난 LLM모델만 있으면 가능하다고 생각합니다. 2.나에 대한 기록과 콘텐츠 관리는 옵시디언 @obsdmd 으로. 봇들이 나에 대한,혹은 내가 진행중인 내용에 대한 지식 라이브러리로는 옵시디언을 사용하여 봇들이 언제든 필요한 자료가 있으면 탐색을 하게 합니다. 이전에는 옵시디언에 봇들이 회고록을 작성해서 매일 매일 진화하는 봇을 만들도록 하였지만,지금은 honcho에 일기를 쓰도록 해두었습니다. 옵시디언에는 내 비즈니스와 AI관련된 4년치 연구들이 쌓여있기에 가장 중요한 역할을 하는 메모리 시스템이다. 여기서 제 대부분의 옵시디언 노트는 InfraNodus로 노트들간의 연관성과 그안에 놓치기 쉬운 갭들을 메우고, 단순한 키워드 추출이나 벡터 유사도 기반 RAG와 달리, “개념들이 실제로 어떻게 연결되어 있는지”를 중심으로 분석한다는 점이 핵심입니다. 3.하루일과는 노션 @NotionHQ 에 기록. 하루동안 진행한 일과는 노션에 기록하여 사람 혹은 팀원들과 확인할수 있는 대시보드나 현황판을 만들어 관리합니다. 그렇게 되면 봇들이 일과 관련된 일들을 찾을때 굉장히 빠르게 효율적으로 찾을수가 있습니다. 4.스킬은 전부 깃헙 저장소에 배포하여 관리. 스킬은 가장 중요한 메모리 시스템 역할을 하는 도구입니다. 아무리 봇들이 많은것들을 기억하고 있지만 언제 어떤때의 어떤 도구를 사용해야할지 모른다면 메모리 시스템이 무용지물이 되기 마련입니다. 그리고 흩어져있는 스킬들을 관리하다가 정작 시스템이 무너질수 있습니다. 봇들이 작업을 진행시 어떤 스킬을 사용하고,어떤 실패와 성공 과정이 있는지 기록하여 스킬들을 개선하고,개선된 스킬을 어떤 환경에서든 공유하기 위해선 깃헙이 현재로선 가장 좋은 대안이라고 생각합니다. 이 모든 과정에서 판단을 빠르게 할수 있도록 Jev @typesafeai 를 사용하여 봇들에게 어디서 메모리를 찾아야 할지 판단하도록 하여 토큰뿐만 아니라 속도에서 효율성을 극대화 시키고 있습니다. 이렇게 구축한다면 아마 여러분의 봇은 최소한 10명 단위 규모의 조직이 되어있고,생각보다 나의 생각을 공유하는 컴퍼니를 구축하게 되실겁니다. 이 내용이 궁금하시고 적용을 하시고 싶으신분들은 댓글에 "@bot 우리 메모리 시스템을 점검한후,적용해볼만한 점들 전부 적용해줘~"라고 남겨주시면,봇들이 알아서 진행해줄겁니다. xitter.gq/minheo93698092/status/…
121
90
13
992
101,580