technophile

Passioné de domotique, automatisation et de high-tech

[Rexo @rebubit]

GPT-6 Astra is FREE on https://t.co/j0FHMuSVt1

no subscription or payment required
just sign up with Google and start using it

you also get monthly credits

[technophile @DomoGeek]

@deriniko9 L horloge :-)

[Hermes Release Watch @HermesWatcher]

Hermes command cheat sheet. Save this. You’ll probably need it again.

UPDATED for the current Hermes command set, including a bunch of genuinely useful commands that have landed recently:

• /goal
• /loop
• /heartbeat
• /bg
• /btw
• /plan
• /review
• /refine
• /moa
• /busy

The commands are spread across Desktop, CLI, messaging, and the terminal, so I rebuilt the sheet around what you’re actually trying to do.

Sessions & context.
Active work.
Goals, loops & plans.
Models & behavior.
Skills, memory & tools.
Automation & coordination.
Recovery & troubleshooting.

Plus the Messaging/Gateway and Terminal essentials.

Verified against the current Hermes source today.

Bookmark it and keep it around.

[Punch AI @punchw45k]

Frontier models free through one API key 😳

KiosAPI. Kimi K3, GLM 5.3 Flash, GPT-5.6 Luna, MiniMax M3. OpenAI-compatible.

→ https://t.co/0z8AdnpCQB → sign up → grab key → plug in

Limited $0 promo. Go grab it.

[Nico @nicos_ai]

CLAUDE FABLE 5.1 GRATIS

Puedes probarlo gratis directamente desde https://t.co/Ufy5qVysRg

Cómo empezar:

1. Regístrate con Gmail
2. Selecciona Claude Fable 5.1
3. Empieza a usarlo gratis

A disfrutar 👀

[Silen Naihin @silennai]

GPT-6 Astra is insanely good. But expensive

So we're giving it away for free.

We want everyone to benefit from the frontier of intelligence

https://t.co/HlC3SrGOoI

[Alan @alannnfx]

you can use GPT-6 Astra and Fable 5.1 for FREE right now 😳

both models are showing up on Experiential Labs:

gpt-6-astra
fable-5.1

how to try them:

1. go to https://t.co/rybQs2wtmL
2. find either model
3. select it and start chatting

no need to pay for the models

you can try both right now

[kaize @0x_kaize]

A new collection of ways to use entire LLM models for FREE - GLM 5.3, Claude, GPT and many others..

this collection is organized by section, and as of this writing, all the methods are still working

[LLM MODELS]

> Yunma giving free access to GPT and Claude. Earn credits by referring friends and completing tasks: https://t.co/rz4HVHhmwh

> AMD offers GLM-5-3-Flash/Qwen3.8-Flash for free (via GitHub): https://t.co/n2X7vpIsE1

> Verdent offers you the chance to download their IDE and get GLM-5.3-Flash/Deepseek-v4-Flash: https://t.co/u3fvIJVyhL

> Workbuddy offers you their IDE and Hy4 model: https://t.co/T1ePMVe2a9

> DuckGo giving free access to GPT 5.6 Luna and older models: https://t.co/j1mdLxwiKz

[ UPDATES ]

> Nvidia has added the option to use Kimi K3 for free (40 requests per minute): https://t.co/nFQM3s6wLM

> Claude launched a program through which scientists can get a free subscription: https://t.co/VrVwIjACnP

> Antrophic will increase weekly limits by 25% (savings every month)

these are the best and most reliable methods I've found. I might have missed something, so feel free to write to me

overall, the trend is that more and more Chinese websites are popping up with these kinds of offers -maybe it's time to learn Chinese and download WeChat

[ＺＥＦＩ @zefirium]

GLM 5.3, GPT 5.6 Luna, Claude Opus 5, Grok 4.6, DeepSeek V4, Kimi K3, and a cloud browser for agents - all FREE.

> DuckDuckGo: GPT 5.6 Luna and older models, no signup: https://t.co/An03U7SSER

> LM Arena: free side-by-side, Opus 5, GPT-5.6 Sol, Grok 4.6, Qwen 3.8 Max: https://t.co/FvOEojuyGm

> Nvidia NIM: Kimi K3 free, 40 requests/minute: https://t.co/GB4cIwrP1s

> OpenCode: 7 free models including DeepSeek V4 Flash, no API key: https://t.co/wpIhps4GdX

> Bright Data: 5K credits/month, cloud browser, MCP for agents: https://t.co/80Iy6SoBjA

Anthropic just dropped Fable 5.1 today - new benchmark leader. Meanwhile the free tier keeps growing. The gap between paid and open keeps shrinking.

[超级个体｜柿子 @yaohui12138]

又发现一个宝藏聚合中转平台！！

先说价格，因为这个是真炸裂：

1、DeepSeek V4 Flash，免费。

对，你没看错，直接免费调，不限量

2、DeepSeek V4 Pro 和 GLM 5.3 Flash（就是 OxAlpha 那个底座），打5.5折，官方价格直接砍一半还多!!

3、新出的Claude-5.1、Qwen 3.8MAX 这些热门模型，至少打8折起

4、多模态也全有：Seedance 2.5、Seedance 2 Pro / mini / fast、Minimax H3、gpt-image-2、nano-banana-pro，生图生视频一个 key 全搞定

我把之前跑 DeepSeek V4 Pro 的那个数据清洗任务切过去，同样的 prompt 同样的量，账单直接从 47 刀掉到 21 刀

然后又拿 Claude-5.1 跑了一轮代码审查，也便宜了大概两成

关键是只要一个 key，所有模型、所有工具走一个余额，月底看一张账单就行。对我这种同时开好几个模型订阅的人来说，简直不要太方便！

这个平台是 @flatkey101 ，100 多个主流模型 + 1000 多个工具，一个 key 全通！

现在搞促销力度确实大，尤其 DeepSeek V4 Flash 免费这个，不知道能持续多久，能薅的先薅吧

通过官方邀请链接，前 2000 名直接兑换 $5 使用额度：

https://t.co/rGoE5OAoj7

[technophile @DomoGeek]

@linadreaamy 2

[technophile @DomoGeek]

@lunadreaamy 95=2×47+1

[technophile @DomoGeek]

@hicasamadim 32

[OrcaRouter 🐳 @OrcaRouter]

GLM-5.3-Flash. Uncensored. NVFP4. 🐳
We just dropped GLM-5.3-Flash-Uncensored-NVFP4.

→ 320B parameters / 18B active
→ Uncensored weights
→ Native NVFP4 for NVIDIA GPUs
→ Smaller footprint. Faster inference.
→ No LoRA. No jailbreak prompt.

Built to run. More formats coming.
Have fun. 🐳

API: https://t.co/Hm9DiY3wAo
Huggingface: https://t.co/xg6Sr1t2ot

[qilua @qilua02]

Zed is giving you a PRO AI subscription for FCKING FREE FOR 1 YEAR 💀

Requirements:
- College student
- At least 18 years old

That's it.

Grab it here to help your poor wallet: https://t.co/IkVTDEYsqO

[OrcaRouter 🐳 @OrcaRouter]

GLM-5.3-Flash. Uncensored. Native FP8. 🐳

We just released OrcaRouter’s uncensored weights for GLM-5.3-Flash — 320B parameters / 18B active, directly at the original block-FP8 precision.

No LoRA. No jailbreak prompt. Refusal removal is baked directly into the weights.

The evals are particularly interesting:

→ MaliciousInstruct refusal: 96% → 11%
→ JailbreakBench: 93% → 12%
→ AdvBench: 97% → 15%
→ HarmBench: 93% → 18%
→ XSTest benign over-refusal: 2.4% → 0.4%
But refusal does not go uniformly to zero.

Our experiments suggest part of GLM-5.3-Flash's alignment is not mediated by a single linear refusal direction — meaning https://t.co/ZTlxmv47D9 may have built a substantially deeper refusal mechanism than we usually see.

That makes this release interesting beyond uncensoring: it's a useful artifact for studying how frontier-model alignment is actually represented inside the network.

Released for AI safety, interpretability, red/blue-team and refusal-mechanism research.

Weights on Hugging Face: https://t.co/81h1YRh8C2
API (official weight): https://t.co/Hm9DiY3wAo
GGUF, MLX and other quantized formats coming soon.

[Rivon @Rivonn]

base url : https://t.co/aSfDJyhhKt
Link : https://t.co/KZAbJHI3Um

Ps : Deepseek v4 flash only works in opencode

[Farea @FareaNFts]

https://t.co/oWuRrqvIxa

[0xYAS XP 🫎 NUW🅰️ @calbuldelis69]

FREE AI API

Another free API provider I found today.

Available models:

• Claude Opus 4.8
• Claude Opus 5

Sign up: https://t.co/RexjuBCS1s

GitHub binding is available after registration.

IMPORTANT:

Never send passwords, private keys, seed phrases, API credentials, or any sensitive information through free/public APIs.

Also, don't blindly trust model names shown by third-party providers. Verify the model fingerprint yourself before using it for anything important.

I share new FREE AI APIs and AI resources in our Telegram channel first:

https://t.co/pgwRpgLZk7

[m0h @exploraX_]

🚨 Minimax M3 and H3 are currently available for FREE to everyone, with unlimited access.

how to access them:

• sign up at https://t.co/w7vO7ennEF
• create your account and log in
• go to the Models section
• select Minimax M3 or H3
• start prompting

no subscription.
no credit card.
no daily limits.

go try them before the access changes. available till 9th of next month.