I share interesting things I find, what I’m learning, and projects I’m trying. Follow me if you like tech, creative stuff, and learning new things. INFJ-T
Sinapore ⇄ Philippines
Joined March 2018
- Tweets1.2K
- Following1.1K
- Followers222
- Likes1.1K
Aivan Monceller retweeted
FLUX 3 Image Klein is here.
Open Weights with the quality of a large frontier model. Customizable and fast.
5.6B parameters and runs on a single consumer GPU.
Native 4K, bounding boxes, and pixel-perfect editing.
Aivan Monceller retweeted
Today we release Open d1: two open-weight multimodal models in our d1 decision model family.
> d1-3B: text + vision
> d1-omni-600M: text + image or text + audio
> Real-time decision making anywhere, from data centers such as @nvidia DGX to RTX workstations to Jetson at the edge.
1/
Aivan Monceller retweeted
A new fine-tuning framework, Halo, just dropped!
And with it, two new recipes for fine-tuning our MoEs:
• LFM2.5-8B-A1B
• LFM2-24B-A2B
LFM2.5-8B-A1B: github.com/Liquid4All/cookbo…
LFM2-24B-A2B: github.com/whitecircle/halo/…
Introducing Halo, the best framework for post-training of open-source models.
Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format.
Star us on GitHub: github.com/whitecircle/halo
Aivan Monceller retweeted
Jev is such an obvious and useful “type” of model. It’s genuinely shocking we were this far into the AI revolution before someone shipped a general purpose classifier.
I bet @CompleteSkeptic woke up every morning and scrolled X half expecting to be ape’d. Well done @typesafeai.
Aivan Monceller retweeted
When using AI to code, be careful about constantly switching between projects. It may not feel exhausting in the moment, but it can burn you out fast.
The goal shouldn't be to create as much as possible. It should be to build useful things and actually finish them.
Aivan Monceller retweeted
Running LFM2.5-2.6B by @liquidai via llamacpp
gguf: huggingface.co/LiquidAI/LFM2…
vram usage: 6.9gb
command:
$ llama-server \
-hf LiquidAI/LFM2.5-2.6B-GGUF:Q8_0 \
--alias LiquidAI/LFM2.5-2.6B \
--port 8000 \
--jinja \
--reasoning-format auto \
-ngl all \
-fa on \
-c 128000 \
--temp 0.1 \
--top-k 50 \
--repeat-penalty 1.1
Requires a CUDA-enabled build of llama-server
thanks @aivandroid for the command
Aivan Monceller retweeted
you now have the ability to
- play with every possible solution to a problem
- refactor everything when you think of better patterns
so many people complaining about the code the LLMs produce, if you're not producing the best software of your life right now something is wrong
Aivan Monceller retweeted
So proud of our security team! They caught, contained & publicly disclosed an attack unlike anything we've seen before, and did it at record speed.
Also massively grateful to @Zai_org: they shared GLM5.2 as open weights (for free!) with the world and it became a key part of our defense.
This is day one for cybersecurity in the age of agents & we're all learning that secrecy is not the answer & that all defenders (not just a few selected ones) everywhere need more powerful models without restrictions, especially open ones!
Aivan Monceller retweeted
Qwen3.8 is launching and going open-weight soon!🌐
With a massive 2.4T parameters, this model is continuously evolving. We believe it’s one of the most powerful model available today, compatible to leading frontier AI models , second only to Fable 5.
You don't have to wait to test it. Just now, the Qwen3.8-Max-Preview made its debut on Alibaba’s Token Plan, Qoder, and QoderWork. Be among the very first to try it out.
Can't wait to hear what you build. Stay tuned! 🚀
Token Plan
international：qwencloud.com/pricing/token-…
China：platform.qianwenai.com/prici…
Aivan Monceller retweeted
It is my belief that many devs right now are not maximizing what they can do with automatic programming because they still look at the code. Doing it makes you the bottleneck. Your time is better invested in new ideas, QA, design, and asking yourself what is your goal.
Aivan Monceller retweeted
Devin Cloud has Windows environment support
I tried it with my markdown editor app. It launched it from a fresh clone and tested the app on its own
Really cool! Great job @cognition
Aivan Monceller retweeted
If GPT 5.6 still requires me to say "no fallbacks please" I think I'll crash out.
Aivan Monceller retweeted
Anthropic's new Opus 4.8 scores 3.6% lower than GPT 5.5 on Terminal-Bench 2.1. Available to compare side-by-side in Cline now.
(They also announced a plan to release new models with higher intelligence than Opus after adding stronger cyber safeguards in the coming weeks.)
Aivan Monceller retweeted
Free $60 for new accounts in @DevinAI
Thanks @cognition
Giving it a spin today
Aivan Monceller retweeted
Coding agents turn code from artifact into materialized view.
The base tables are the ideas — algorithms, protocols, semantic contracts. The code is one projection. For decades we treated the artifact as authoritative because regenerating was expensive. It isn't anymore.
