←
Subconscious25 posts
Subconscious avatar✓

Subconscious ✓

@subsysdev

The inference provider for long-running agents

◷ Joined June 2025
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·Oct 7

If you start using Nori for cloud agents, make sure you use Subconscious for inference 🤝

Post attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·Oct 22

Build your exploit factory and protect your product!

Post attachment
1:52
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·Jul 14

Pumped to be a part of this event with @baseten and @CapitalG. Baseten has been a killer partner for us, and I'm always thankful for a platform to spread the word of Subconscious 📣📣

Post attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·Jun 27

GLM 5.2 live on the Subconscious API - Frontier coding ability - Powered by our inference system optimized for agents 95%+ cache hit rate, fast token throughput, longer context reasoning with automated nearly-lossless context compression. Check it out.

Post attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·Jun 27

We designed an inference runtime specifically tuned to run agent workloads with a prefix *and* suffix cache, aka when you prune stuff in them middle you still get a 100% cache hit on the tokens around it. We see a 95% cache hit rate for our team's coding agent instance w/ GLM.

Post attachmentPost attachment
Hongyin Luo avatar
⟳ Subconscious retweeted
Hongyin Luo@lhyTHU·Jun 22

GLM-5.2, the latest frontier coding model, can now control and compress its own context in inference time, powered by Subconscious Cache. Model-driven context engineering will be the future of AI Agents. subconscious.dev/blog/subcon…

Dedalus Labs avatar
⟳ Subconscious retweeted
Dedalus Labs@dedaluslabs·Jun 11

Last week at NY Tech Week, founders and builders filled the room for our BYOA (Bring Your Own Agents) workshop. Everyone brought new ideas and their own agents to showcase and try new tools from us and our partners. Big thank you to our co-host @Mercury, and to @paysponge and @subsysdev for joining us!

Post attachmentPost attachmentPost attachmentPost attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·Jun 25

This company puts GPUs on top of water heaters, and uses the GPU to heat the water. It's an incredible company, and we're excited to power agents on this distributed inference network. More info below!

Post attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·May 21

Launch of our TIM-Qwen3.6-27B Model today. We took a great, small Qwen model and substantially improved it's performance: - 1M+ context window (10x extension) - Run 3x as many concurrent runs - 75% less memory required - 1.5x token throughput - OpenAI / Anthropic SDK compatible

Post attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·24 Jul 2025

If you haven't tried the Subconscious playground, here's a look. I gave the model search tools, asked it to tell me about our research paper, and boom, we have a personalized deep research agent. Took 15 seconds to make.

Post attachment
AK avatar
⟳ Subconscious retweeted
AK@_akhaliq·23 Jul 2025

Beyond Context Limits Subconscious Threads for Long-Horizon Reasoning

Post attachment
Jack O'Brien avatar
⟳ Subconscious retweeted
Jack O'Brien@thejackobrien·23 Jul 2025

Today we're launching Subconscious: a new platform for building agents with long-horizon reasoning and tool use, backed by MIT research. One API call. Tool use. Context beyond existing limits. If you're building agents, let's talk.

1:45