Filipe (@bitlamas) header
Filipe (@bitlamas) profile picture

building

Québec
Joined January 2013
Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)Photo by Filipe (@bitlamas)
qwen3.8-flash-next & qwen3.5-9b co-development jam session ibiza hits 2016
7
control freaks won btw
5
bask yourself in the macro while living in the micro
4
universe-breaking prompt: "is this the best you can do?"
17
basé
Replying to @Polymarket
Good. Quebec should separate.
23
if you have a 128 GB AMD Strix Halo running Windows, you can run Qwen3.8-Flash-Next on my custom 102 GB quant (Q4_K_XL) at ~22 tok/s using MTP speculative decoding. don't abuse browser tabs though... the RAM pool gets razor thin (~1 GB free). enjoy: huggingface.co/bitlamas/Qwen…
1
81
sonnet and haiku are much cooler than opus and fable
21
building is fun
2
23
stop using the word "labs" in your stupid startup
2
47
Laguna S 2.1 is one of the best models in its class. Consumer platforms like Strix Halo with 128 GB unified DDR5 are often overlooked in LLM benchmarks, so I'm running my own benchmark gauntlets based on real workloads. So far, it's a very promising contender. Full results soon.
Today we are releasing Laguna S 2.1. At 118B total parameters, with 8B active per token, it does the work of models several times its size on agentic coding. It is remarkably persistent across long-horizon tasks. And it is small enough to run on a single NVIDIA DGX Spark. It is far more capable than anything we have created before, and I think it redefines what a model in its weight class can do. Laguna S 2.1 is an important model for Poolside. What it represents is even more important. If, five years ago, I had read a book that said that by 2030 everything economically valuable, scientifically interesting, and personally meaningful would be built on intelligence contracted from three or four companies, I would have called it dystopian science fiction. We are at a fork in the road of what kind of world we can have. I believe intelligence should and will become a commodity. The question is whether that intelligence comes from three companies, or from many people who can build it, own it, and shape it. The open ecosystem will not win by being the best in its own category. No one cares who is king of the open-source kingdom. People want the best intelligence for the task they are trying to do, with the right balance of quality, speed, cost, and control. If we want a different future, open models have to be on par with, or better than, their closed equivalents. Laguna S 2.1 is a meaningful step in that direction: capable enough to compete far above its weight class, efficient enough to run on hardware you can own, and open-weight so anyone can build on it. Open-weighting our models is the contribution we can make today toward a world where intelligence can be built and owned by many. And we will keep doing it. I am very proud of this team’s work. A big shout out to everyone at Poolside who made this possible, from infrastructure and data to architecture, pretraining, post-training, evaluations, and inference. Laguna S 2.1 is available today under the OpenMDW-1.1 license, with weights on Hugging Face and access through OpenRouter and our API. We are building toward a future where the most capable intelligence in the world can be owned and shaped by anyone. Laguna S 2.1 is one step. We are going to keep building until that future exists. poolside.ai/blog/introducing…
1
4
530
tired of having your Claude Code vibecoding session disrupted because you didn't monitor your limit usage? i got you. meet my Windows (soon macOS/Unix) system tray app and know at a quick glance whether you can keep going crazy or if you should start winding down.
2
145
chatgpt not too shabby making slight edits on images. faster than my gimp skills.
1
94
90s middle-class kids from non-prosperous countries had an organic path to computer wizardry. i remember at 10 i was editing the Windows registry, running NO$GMB to play Pokémon Red, cracking pirated games. buying originals was out of reach but at least i ended up learning a lot.
1
91
vibe coding is not enough, you need to be vibe double-checking your LLM decisions from time to time because of pic related.
1
1
93
frameworks are bloatware
1
61
Filipe retweeted
There’s a coming-of-age moment when you realize 90% of people are lazy and retarded
55
163
29
2,603
529,851
every markdown editor i tried was missing something i wanted or was too bloated, so i built my own. meet Paddown: light on RAM, ~3mb installer, md-only project sidebar, formatting toolbar (normie-friendly!), and other cool stuff. check it out :-)
1
1
105