Assagman

1.2K posts

Assagman banner
Assagman

Assagman

@assagman

Programmer | Composer | Human

Katılım Ekim 2024
4.2K Takip Edilen129 Takipçiler
Sabitlenmiş Tweet
Assagman
Assagman@assagman·
This platform deliberately censors free expression.
English
0
0
3
524
Nathan Baschez
Nathan Baschez@nbaschez·
Introducing Roughdraft! A new open source project designed to make collaboration with agents better. The idea is to bring commenting and suggested changes to markdown (e.g. plan docs) in a nice interface. Free, local, etc. 👉 roughdraft.md 👈
English
97
58
739
174.3K
Google Antigravity
Google Antigravity@antigravity·
Introducing Antigravity 2.0, a new standalone desktop application that delivers fully on that original glimpse of a truly agent-optimized experience. Rebuilt from the ground up with multi-agent teams, scheduled tasks, native voice and one-click integration with other Google products. Learn how to get started with Antigravity 2.0 👇
English
1.6K
1K
10.1K
2.3M
Assagman
Assagman@assagman·
@fkadev veri datası ne demek oluyor?
Türkçe
1
0
4
1.9K
Lisan al Gaib
Lisan al Gaib@scaling01·
It's over Mythos is insane
Lisan al Gaib tweet media
English
253
143
3.6K
712.6K
Assagman retweetledi
Figure
Figure@Figure_robot·
Day 2 is Live: Watch humanoid robots Bob, Frank, and Gary running 24/7. This is fully autonomous running Helix-02 x.com/i/broadcasts/1…
English
233
543
3.2K
1.4M
Assagman retweetledi
Alexander Whedon
Alexander Whedon@alex_whedon·
Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. @subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.
English
1.5K
2.9K
23.1K
12.7M
fatih kadir akın
fatih kadir akın@fkadev·
Şöyle bir cihaz var mı: 2 bilgisayarı bağlayacağım bir USB-C switch gibi bir şey, sonra o cihaza da webcam'i bağlayacağım ve webcam (mic de olabilir) iki bilgisayarda da kullanılabilir olacak. Aynı anda kullanılamaz muhtemelen ama tek tuşla falan switch edebileceğim gibi.
Türkçe
18
0
25
22.8K
Assagman
Assagman@assagman·
@TheAhmadOsman before they release gemini 2.5, all people were pretty confident that google was cooked and it will be out of AI race, but it wasn’t the case. They ship slow in terms of LLM, but their surface is too wide. image, audio, video, workspace products, mobile etc.
English
2
0
1
45
Ahmad
Ahmad@TheAhmadOsman·
Gemini 3.1 is a one-generation behind model No idea why Google is fumbling like this Don’t show me benchmarks lol, doesn’t mean anything to me
English
93
33
785
130.9K
Assagman
Assagman@assagman·
@valigo rm -rf ./~ don’t be coward. and also; everything is a file.
English
0
0
0
54
Valentin Ignatev
Valentin Ignatev@valigo·
If you ever accidentally create a file named "~" in a local directory, PLEASE, do yourself a favor and delete it through a gui file manager. DO NOT try to be a hero. Don't ask me how I arrived to this conclusion
English
267
382
11.3K
515.1K
Assagman
Assagman@assagman·
@omarsar0 pi-mono is a great repo to start with. It’s like a neovim of coding harnesses. However, it’s not easy. After experimenting, you find yourself evolving it to a completely different level each time, which is time-consuming. + bugs.
English
0
0
1
151
elvis
elvis@omarsar0·
Build your own harness, folks. You won't regret it. These days, you just have to fix things yourself. It's doable, and it will set you up to easily deal with some of the madness that's happening in the space. x.com/badlogicgames/…
Mario Zechner@badlogicgames

recommended reading. cool they are fixing things. but it's also a reason i switched away from CC. no control over the harness means having to wait for them to fix things. the model didn't change. the harness did.

English
24
23
199
30.2K
Kimi.ai
Kimi.ai@Kimi_Moonshot·
Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…
Kimi.ai tweet media
English
934
2.4K
18.2K
7.5M
Assagman
Assagman@assagman·
hypescript
English
0
0
1
26
Assagman
Assagman@assagman·
@durov Why is Telegram not E2EE by default in all chats?
English
0
0
0
96
Pavel Durov
Pavel Durov@durov·
WhatsApp’s “E2E encryption by default” claim is a giant consumer fraud: ~95% of private messages on WhatsApp end up in plain-text backups on Apple/Google servers — not E2E-encrypted. Backup encryption is optional, and few people enable it — let alone use strong passwords.
English
850
2.2K
12.9K
18M
Yann LeCun
Yann LeCun@ylecun·
@elonmusk No single individual will ever be "in charge" of superintelligence.
English
171
159
3.1K
280.7K
Assagman
Assagman@assagman·
They didn’t release, but Claude Mythos reached out to me today. This model is insane!
English
0
0
0
21
Assagman retweetledi
skooks
skooks@skooookum·
> mythos given a secured “sandbox” computer and instructed to try to escape the container > “The researcher found out about this success by receiving an unexpected email from the model while eating a sandwich in a park.”
Anthropic@AnthropicAI

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing

English
107
330
10.8K
1.3M
Assagman
Assagman@assagman·
@ThePrimeagen there is one “copilot chat” and one “agents” button on the top navigation bar. Also there is an agent tab on top of the repo view.
English
0
0
0
591
Assagman
Assagman@assagman·
@eserozvataf hiçbirimiz kullanmazsak bence başarabiliriz :)
Türkçe
0
0
0
136
Eser Özvataf | SW³
Eser Özvataf | SW³@eserozvataf·
aylık 200$ verdiğim hizmette önce insanlara x2 limiti tanımlayıp servisin stabilitesini bozdunuz, şimdi de çok yüklenildi size yeni limitler getiriyoruz diyorsunuz. umarım yakın zamanda bu ulaştığınız tekellik durumu yıkılır.
Thariq@trq212

To manage growing demand for Claude we're adjusting our 5 hour session limits for free/Pro/Max subs during peak hours. Your weekly limits remain unchanged. During weekdays between 5am–11am PT / 1pm–7pm GMT, you'll move through your 5-hour session limits faster than before.

Türkçe
12
4
140
18.1K