We made the first AI model you can have a realistic conversation with that was trained entirely on speech!
Dessa is a full-duplex speech-to-speech model that you can run on consumer GPUs.
This is a GPT3 moment for speech.
Hey @grok! I’m about to smash buy Bitcoin. Which gives me the most sats per dollar: Strike, River, Fold, or Cash App?
Compare BOTH fees and spread using the same purchase amount. Rank them from best to worst.
@TechnoYukionna@summerswatchful It’s a joke, buddy. Nobody can see shit in that pic. Have a wonderful day or night. I’m sure you’re at the top of the list. 🫶
Day 14/
Small quality of life improvement. You can now edit previous messages within a thread in the desktop app. Long time requested, and took way too long to get that one out.
@cosmintrica@thsottiaux Never going to understand why people on Plus think they can use more than Luna. Hell, I’m on Pro and still use Luna Fast 99% of the time and it never messes up….
A recent warning said AI could break Bitcoin “soon,” prompting “bunker mode” talk. No such attack exists. I made this video to explain why there’s no need to panic, about this or quantum computers, and what it means in light of Russell Impagliazzo’s five cryptographic worlds. 🧠
We are releasing Ultramarine 1 Flash, a frontier-class model built for knowledge work. It is open-source and achieves similar performance to Fable 5, while being 60x cheaper.
It was post-trained by a team of 5 for ~$300k all-in. Available on API now, with weights releasing in 2 weeks.
THIS IS ACTUAL F*CKING GOLD
Anthropic just quietly dropped one of the best setups for Claude Code
The rule: orchestrate Sonnet, Haiku and Opus 5.5 simultaneously, locking every model into the exact lane it dominates
Opus-grade intelligence on critical architectural calls, zero Opus burn on routine terminal iterations
Launch Claude Code with this flag pair:
claude --model sonnet --advisor opus
how the workload divides:
→ Sonnet 5.5 leads the main session and cuts the actual code
→ Haiku 5.5 swarms repos, greps call sites, and parses docs concurrently
→ Opus 5.5 remains on standby as advisor for high-leverage checkpoints
→ you eliminate token waste on work that never required frontier reasoning
Opus only gets triggered on three specific events:
→ right before locking an architectural plan
→ the second an identical error hits twice
→ right before marking a complex task complete
Sonnet builds · Haiku explores · Opus reviews
JEV engineering applies the exact same logic one layer deeper: deterministic branches (file selection, tool dispatch, fast retry vs abort) clear in sub-milliseconds, so the frontier models only handle genuine forks
the architecture tree:
> Sonnet 5.5 drives the primary terminal session and edits code
> search crawls repo structure on Haiku 5.5
> grep locates call signatures on Haiku 5.5
> docs fetches API specs and schemas on Haiku 5.5
> Opus 5.5 stands on call as advisor, ingesting full context when pinged
> JEV resolves instant deterministic routing
feed this tree and prompt directly into Claude Code ↓
"Configure my Claude Code environment around this multi-model tree:
1. Run the primary session on Sonnet 5.5 with Opus 5.5 as advisor
2. Spawn three read-only Haiku 5.5 subagents: search (repo mapping), grep (call sites), docs (API references)
3. Enforce one rule in CLAUDE.md: ping advisor before locking any plan, upon repeating any error twice, and before final task handoff
4. Route instantaneous deterministic forks (tool choice, path check, retries) through JEV
Show every file update as a diff first, make zero changes without confirmation"
↳ https://t.co/gvAWk6JDNP
bookmark this, you'll run it every single day