bonham

more models, more inference

[Sam Hogan 🇺🇸 @samhogan]

We're introducing Project AELLA, in partnership with @laion_ai & @wyndlabs_ai

AELLA is an open-science initiative to make scientific research accessible via structured summaries created by LLMs

Available now:
- Dataset of 100K summaries
- 2 fine-tuned LLMs
- 3d visualizer

👇

[Inference @inference_net]

Today, we release LOGIC: A novel method for verifying LLM inference in trustless environments.

- Detects model substitution, quantization, and decode-time attacks
- Works out of the box with @vllm_project, @sgl_project, @openrouter, and more (just need logprops)
- Robust across GPU types and hardware configurations
- Low computational overhead (~1% of total cost)

Blog: https://t.co/FbV5sG5Lbq
Code: https://t.co/nLkuJZ1liJ

[Sam Hogan 🇺🇸 @samhogan]

Using custom-trained LLMs and > 1k 4090s to visualize 100k scientific research papers in latent space 🌐

DM me for early access 🔜

[bonham @bonham_sol]

@samhogan @inference_net @multicoin @a16zcrypto @topology_vc @fdotinc LGTM

[bonham @bonham_sol]

SLMs coming to an @inference_net provider near you

[bonham @bonham_sol]

Real inference demand coming to an Inference Devnet near you soon thanks to our proprietary inference verification mechanism.

[bonham @bonham_sol]

@samhogan uwu

[bonham @bonham_sol]

Stake and secure the world's largest distributed GPU network #inference

[bonham @bonham_sol]

The first @inference_net Devnet epoch has been completed. Only possible on @solana - Thank you to everyone in the community supporting us.

[Inference @inference_net]

The Inference Epoch 3 devnet airdrop is live!

The devnet staking protocol will activate today at 4pm PST.

Claim your tokens on Solana devnet 👇

[Inference @inference_net]

Epoch 3 has begun.

Join us.

[bonham @bonham_sol]

@solflare how can get around this to test a program flow on Solana devnet?

[bonham @bonham_sol]

@jacobvcreech @samhogan We are trying to gather a lot of devnet SOL for some program testing, and it's difficult to do because of the rate limiting that exists in the main faucet or in the normal RPC endpoint.

[bonham @bonham_sol]

@jacobvcreech @samhogan I consistently get a 500 error in the UI when trying to use the main faucet with a GitHub account connected.

[bonham @bonham_sol]

@samhogan Time to pack it up

[Sam Hogan 🇺🇸 @samhogan]

token volume from @inference_net on @openrouter

a little choppy but you get the idea 📈

[Inference @inference_net]

start your engines

[Sam Hogan 🇺🇸 @samhogan]

Inference .net is hiring a Developer Relations Lead in San Francisco! If you:

- Love working with AI to amazing build products
- Have experience creating world-class educational content for developers
- Enjoy solving developer problems and fostering community growth

We want to hear from you. Please send relevant information including GitHub, LinkedIn, and something amazing you have built to sam @ inference .net.

If you introduce us to someone we hire, we will pay you a $10k CASH referral bonus.

Full job description below 👇