Open-source at its finest.
Fireworks was listed as supported, but EvoSkill didnโt fully recognize it until @0xHermes_ documented the โunknown providerโ bug behind the crashed calls.
Now EvoSkill v1.3.0 ships with first-class Fireworks support โ
Fireworks AI is now live on EvoSkill v1.3.0!
You can now use @FireworksAI_HQ directly with EvoSkill to run fast inference on open models as both the evolution harness backend and the LLM scorer.
Alongside Claude API and OpenRouter, Fireworks AI is now a first-class provider
๐จ BREAKING: ANTHROPIC MOVES TO TOTALLY SHUT CHINA OUT OF CLAUDE
Anthropic is sealing loopholes that allowed Chinese-linked users to access Claude despite its ban, per FT.
Chinese firms reportedly used VPNs, cloud platforms and proxy โtransfer stations,โ to bypass restrictions.
Sentient AI researcher @edoardocontente was featured in Forbes for his perspective on AI agents.
His point: capability doesn't always equal trust, which is why his work at @SentientAGI focuses on building verifiable and auditable models via open-source AI.
EvoSkill has now been cited by 56+ papers.
From frontier AI labs at Microsoft Research (@MSFTResearch) and Tongyi Lab (@Ali_TongyiLab), to top universities such as National University of Singapore (@NUSingapore) and Columbia University (@Columbia), researchers around the world
Sentient Foundation is launching a 42MM grants / investment program to empower developers and companies to build open source AI.
The gap between open source and closed source models / frameworks is tightening.
We want to accelerate the pace of innovation of open source ai via
The most important technology of our time is being built in private, but we're funding the alternative: $42M for the people building AGI in the open.
Whether it's the model, weights, code, data, or evals, AI should belong to the people it serves, run on hardware they own, and
What happens when you combine RAG filtering with parallel execution?
The RAG-filtered agent called fewer tools per query while maintaining answer quality, producing outputs with 0.85 embedding similarity.
TLDR: Sentient researcher @khetan_sarvesh found that agent efficiency
Lots of complex production agents actually use RAG for tool filtering or prompt selection, and yet there is barely any information about it. We decided to fix that.
When your agent has 40+ tools, brute-force selection breaks down. We measured how embedding-based filtering and
Community-driven AI development needs more than good intentions.
Thatโs why @sentient_found is committing $42M to support open-source AGI builders โ
The most important technology of our time is being built in private, but we're funding the alternative: $42M for the people building AGI in the open.
Whether it's the model, weights, code, data, or evals, AI should belong to the people it serves, run on hardware they own, and
ๅฝ AI ่ฟๅ ฅ็ๅฎไธ็๏ผไธบไปไนไธไธไปฃๆบ่ฝๅฟ ้กปๅผๆพใๅฏ้ช่ฏใๅฑไบๆฏไธชไบบ๏ผ
ๅฝ AI ็่ฝๅ่ถๆฅ่ถๅผบ๏ผๆไปฌ็ๆญฃ้่ฆ่ฟฝ้ฎ็๏ผๅทฒ็ปไธๅชๆฏๅฎโ่ฝๅไปไนโ๏ผ่ๆฏ๏ผๅฎๆ็ปไผไธบ่ฐๆๅก๏ผๅ็ฑ่ฐๆฅๆๅๆงๅถ๏ผ
ไปๆฎ้ไบบๅจๆญ็ฝใๆถจไปทใๅ่ฝไธ็บฟๆถๅคฑๅปๅทฅๅ ท๏ผๅฐไธชไบบๆฐๆฎใ่บซไปฝใ็ฎๅไธๅฏไฟกๆง่ก้ๆธๆไธบ AI
Applications for the Open Source AGI Grant and Investment Program are open.
If you believe AGI must remain open, decentralized, and aligned with humanity's interests, you already qualify.
Open technologies are essential to ensure the benefits are broadly distributed and
Most AI money flows to whoever already has the compute, the data, and the distribution. Sentient Foundation, the team behind @SentientAGI, is funding the other direction with $42M for people building open, private, useful AI.
The part worth reading twice: the grant track is
