Viewing profile — campers

Interested to try it out! Some feedback on the homepage there's nothing above the fold, or directly below that says its a Legal AI platform. I would like a legal AI tool, but I'm n…

I had wondered if they run their inference at high batch sizes to get better throughput to keep their inference costs lower. They do have a priority tier at double the cost, but ha…

OpenAI and Nvidia's 10GW datacenter agreement and Sam Altmans new blog post wanting to build 1GW of infra a week made me think of this article again and to post it up. Here's a cou…

I added a key rotator to my AI coder, and asked a couple of friends to make keys for me. That helped code a good chunk of http://typedai.dev when 2.5 Pro came out

Google actually does provide that service! https://cloud.google.com/vertex-ai/generative-ai/docs/model-...

Looking forward to using this on Cerebras!

I've been thinking about adding in an agent to our Codex/Jules like platform which goes through the git history for the main files being changed, extracts the Jira ticket ID's, loo…

There is a huge focus on training the LLMs to reason, that ability will slowly (or not that slowly depending on your timeframe!) but surely improve in the AI models given the garga…

There isn't a TypeScript runtime, it is just a JavaScript/ECMAScript compiler/transpiler with a type checking and language server

The price will come down over time as they apply all the techniques to distill it down to a smaller parameter model. Just like GPT4 pricing came down significantly over time.

I get the same feeing when I first looked at the LangChain documentation when I wanted to first start tinkering with LLM apps. I built my own TypeScript AI platform https://typedai…

https://typedai.dev is another full-featured one I've built, with a web UI, multi-user support, code editing agents, CodeAct autonomous agent

https://web.archive.org/web/20230812020202/https://www.youtu...

If an AI achieved 100% in this benchmark it would indicate super-intelligence in the field of mathematics. But depending on what else it could do it may fall short on general intel…

On Google Cloud a server with 8 TPU v5e will do 2175 token/seconds on Llama2 70B. https://cloud.google.com/blog/products/compute/updates-to-ai... From https://cloud.google.com/tpu/…

The first implementation of inference on the Wafer Scale Engine and utilized only a fraction of its peak bandwidth, compute, and IO capacity. Today’s release is the culmination of …

A bit like the new Gemini Pro 1.5-002 release.

The tl;dr on high level performance improvements "The scaling curves indicate that Diff Transformer requires only about 65% of model size or training tokens needed by Transformer t…

Check out https://sophia.dev Its AI tooling I've built on top of Aider for the code editing. I initially built it before Aider added support for running compile and lint commands, …