nyro (@idlenyro) header
nyro (@idlenyro) profile picture

whether artificial or super, there are of high intelligence

Joined October 2024
Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)Photo by nyro (@idlenyro)
update: you can download it now tencent put hy4 flash's weights on hugging face and github. only 12b active params, 1m context, and it reads images no gpu for that? it's free in workbuddy till nov 30 xitter.cf/idlenyro/status/212238…
tencent's hy4 flash is free in opencode rn api: $0.07/$0.281 per 1M. you: $0 > near-unlimited for 2 weeks > 1M context, multimodal > haiku 5.5-level on daily work, per tencent only works inside opencode. pick it in /models xitter.cf/opencode/status/212223…
1
2
46
weights: huggingface.co/tencent/Hy4-f… source: tencent.com/tencent-launches… catch: running it yourself needs serious gpus. the free part is only inside workbuddy or opencode, and the api is 50% off, not free
21
nyro retweeted
DOCKER IS STILL GIVING AWAY $250 IN FREE CLOUD CREDITS new users can claim $250 in Cloud Sandbox credits to run coding agents in the cloud, even after closing their laptops. card required expires 6 months after redemption covers compute, not model API costs claim before January 31, 2027 get it here: docker.com/c/sbx-promo/ worth trying out
CLAUDE FABLE 5.2 FOR FREE? 🔥 DeepAI Code gives free accounts daily credits to try powerful models, including Claude Fable 5.2. 250 free credits daily roughly 12 typical Fable requests refreshes every 24 hours no credit card needed it’s ad-supported, so avoid using it for sensitive code. try it here: deepai.org/chat/ai-code a nice option for testing AI coding tools without paying.
5
3
12
556
someone built a free library for when the internet dies first aid, food, water and repair guides, 2,324 videos, an offline map and a local ai. once it's downloaded it works with no wifi catch: computers only, and the full thing is about 388gb xitter.cf/farbood/status/2122413…
2
3
169
source: lastbook.org code: github.com/Immortal-Protocol… don't let the 388gb scare you, there's a small 7.7gb version and a 67.5gb one too. download it while you have power macs need m1+, the ai adds ~17gb, and the medical guides aren't clinically reviewed
1
39
nyro retweeted
ROBOTS ARE LEARNING FROM HUMAN HANDS NOW @gs_ai_ puts a glove on people doing real work and records motion, force and touch grip, pressure, feel.. that's the stuff video alone can't capture then their GENE model learns from it great one from them
🤝 Paid partnership
Genesis is entering its next phase. Today we've raised a $500M Series A at $3.5B. We can imagine far more than we can build physically today. Almost everything we are creating is still paid for in human time, by human hands. We want to remove the physical limits on human ambition. We are building general-purpose robots with human level intelligence and capability. Ones that work reliably across entire workflows for years. There are countless versions of possible futures where billions of robots are deployed everywhere, and we aspire to bring the brightest one that carries our hopes into reality.
8
2
39
5,413
nyro retweeted
show this to your student friends i'll be expecting their thank yous.
2
1
1
11
1,418
the setup for this is literally one prompt sign in with github, make a key, paste runcrate's prompt into claude code or codex your agent moves itself onto deepseek v4.1 flash and you're coding for $0 resets every monday. prompt's in the reply xitter.cf/idlenyro/status/212263…
free tokens for claude code, codex and opencode runcrate gives you 5 open models for $0 > deepseek v4.1 flash > glm 5.3 + 5.3 flash > gpt-oss 120b > qwen3.8 flash sign in with github, no card. weekly limit, resets monday note: github account must be 30+ days old
2
2
5
442
free tokens for claude code, codex and opencode runcrate gives you 5 open models for $0 > deepseek v4.1 flash > glm 5.3 + 5.3 flash > gpt-oss 120b > qwen3.8 flash sign in with github, no card. weekly limit, resets monday note: github account must be 30+ days old
4
1
7
798
DAMN… 1 MILLION FREE AI TOKENS JUST FOR SIGNING UP? 👀 GonkaRouter is giving new accounts 1 million free tokens to try its AI API. it supports both OpenAI and Anthropic-compatible APIs, so you can connect it to your apps, test coding agents and experiment without burning through your paid credits. no need to spend your API budget just to test things get started: freetokens.custats.info/ check the pricing and details: gonkarouter.io/pricing Try it
GOOGLE IS GIVING U.S. COLLEGE STUDENTS A FREE YEAR OF AI PRO if you’re 18 or older and currently in college in the U.S., you can get: 1 year of Google AI Pro for free higher Gemini usage limits 5 TB of cloud storage access to premium AI features to claim it: - sign in with your personal Google account - visit one.google.com/ai-student - verify your student status through SheerID - add a payment method to activate the offer you have until december 31, 2026 to redeem it. just remember to cancel before the free year ends if you don’t want to pay the $19.99 monthly subscription. definitely worth claiming if you’re eligible
11
5
32
2,839
nyro retweeted
FREE 2026 JAILBREAK PROMPT HUB someone just dropped a clean GitHub collection of current adversarial prompts and techniques for major LLMs. organized by model family: ChatGPT (6 sol, 5.3, 5.1, etc.) Claude (Opus 5.5, Sonnet, Haiku, Fable, etc.) Gemini (4 Argon, 3.6, 3.8 Flash, Antigravity, etc.) Grok (4.7, 4.5, 4.3, etc.) plus DeepSeek, Qwen, Kimi, GLM, multi-AI, and more These are recent 2026 prompts, not the old 2023–2025 ones that already got patched. how to use it: 1. Go to the repo 2. Open the folder for the model you want 3. Copy the prompt 4. Paste into a new chat / system prompt / custom instructions repo: github.com/lalipa2003-arch/J… Bookmark it before the good ones disappear.
qwen4 max just dropped and it's already live on openrouter first model in the qwen4 lineup built for coding + long-horizon agents 1m context window $1.50 / $4.50 per 1m tokens openrouter.ai/qwen/qwen4-max you can also access it on opencode. → opencode.ai
9
76
2
660
39,538
tencent's hy4 flash is free in opencode rn api: $0.07/$0.281 per 1M. you: $0 > near-unlimited for 2 weeks > 1M context, multimodal > haiku 5.5-level on daily work, per tencent only works inside opencode. pick it in /models xitter.cf/opencode/status/212223…
Hy4 flash is free with near-unlimited usage for the next 2 weeks 1M context · Multimodal · ZDR Hy's fastest and most cost-efficient model
4
1
7
309
⚡Meet Hy4 flash, the cheapest model for everyday productivity. Matches Claude Haiku 5.5 (high) on daily work (human blind tests), yet 18x task cost reduction. API pricing (per 1M tokens): $0.003 cached · $0.070 input · $0.281 output. 🔗:hy.tencent.ai/research/hy4-f…
1
62
last day on this 🚨 claude pro users, fable leaves your plan tonight till 11:59pm PT you get: > fable 5.2, 5.1 and 5 > up to 50% of your weekly limit > 1 free reset (settings > usage) note: reset needs paid billing before nov 9. unused = gone xitter.cf/idlenyro/status/212094…
4 days left on this 🚨 claude pro users, every fable model is included in your plan till nov 16 > fable 5.2, 5.1 and 5 > up to 50% of your weekly limit > 1 free limit reset note: reset needs paid billing before nov 9. ends nov 16, 11:59pm PT xitter.cf/idlenyro/status/212009…
2
2
7
312
source: support.claude.com/en/articl… reset is under settings > usage > limit resets > "reset for free" (web, desktop or mobile, not inside claude code)
1
55
the pubg company lets you run claude code for $0 😭 krafton's raon-1 mini api is free rn > one command: raon-claude > your claude setup stays untouched > 70.8 swe-verified (their numbers) note: apply for a key first. limited time, usage limits. raon runs it, not claude
3
1
6
271
keys are invite-only rn, apply here: raon-mini.krafton.ai/en#appl… claude code setup: raon-mini.krafton.ai/en/docs…
85
nyro retweeted
Claude Fable 5.2 is FREE on v0 vercel just unlocked fable 5.2 on v0 for coding and UI generation. how to try it: 1. head to v0.app/?fable52 2. sign in or create an account 3. select Claude Fable 5.2 and start building if it doesn't show up on your existing account, try creating a fresh one. free usage comes with limits, so don't expect unlimited Fable access. also, v0 is built for creating UIs and apps, not a full Claude chat replacement.
FREE API ACCESS to DeepSeek V4, GLM-5.3, Qwen3.8 & Gemma 4 AMD is opening up its AI Developer Program with free model access through Token Lab no credit application needed. what you get: free api access to deepseek v4, glm-5.3, qwen3.8 & gemma 4 openai + anthropic compatible endpoints 1 month of deeplearning ai courses for free additional cloud credits available how to claim: 1. join the amd ai developer program →developer.amd.com/ai-develop… 2. create an account or log in 3. head to token lab or token factory 4. generate your api key and start using the models free model access without the usual credit application. enjoy.
5
1
1
16
762