AI agents are only as useful as the infrastructure behind them. @ricoh is running custom Japanese AI models on SambaCloud at 700+ tokens/sec, delivering up to 10× faster performance than previous infrastructure. What once took a minute now finishes in ~10 seconds, making
LLMS
-
LFM2.5-8B-A1B running as local Blender assistant demo
By
–
LFM2.5-8B-A1B running as a Blender assistant locally. Beautiful demo! https://t.co/uTZB3zOgrn
— Maxime Labonne (@maximelabonne) 1 juin 2026LFM2.5-8B-A1B running as a Blender assistant locally. Beautiful demo!
-
Ethan’s deep dive on xAI’s SOTA video world model training
By
–
This pod was an incredible gift to the community:
— swyx (@swyx) 1 juin 2026
not only our first pod about @xAI, but Ethan really indulged on all our questions on how to train a SOTA Videogen world model, including specific areas (consistent extending/editing, voice) that Grok @Imagine is *still* SOTA,… https://t.co/purQe9Ja81 pic.twitter.com/Sl4AqAt7RAThis pod was an incredible gift to the community: not only our first pod about @xAI
, but Ethan really indulged on all our questions on how to train a SOTA Videogen world model, including specific areas (consistent extending/editing, voice) that Grok @Imagine is *still* SOTA, -
Longmemeval Experiment: Three Ingestion/Extraction Configurations Compared
By
–
longmemeval experiment arch: 1) deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval)
2) semantic ingestion/extraction (84.8% accuracy, 94.9% retention)
3) semantic ingestion/deterministic extraction (87.6% accuracy, 90.0% retrieval) this was staggered, not -
Ask AI directly, provide context, and define success
By
–
codex tip that sounds obvious but somehow isn't: if you want it to do something, just ask it if it keeps messing up the same thing, ask it to remember what to avoid next time tell it what good looks like and what context it should use you'd be surprised how often this works
-
Elon Musk calls ‘test-time compute’ a dumb AI term
By
–
“Test-time compute” is such a dumb name for “compute”. So many dumb names for things in AI.
-
Open source weights and 1m context win
By
–
Yeah, but opensource and weights and 1m context. So I’d say it’s a win
-
M3: MiniMax’s latest model with 1M-token context and agentic reasoning
By
–
M3 is MiniMax's latest model: 1M-token context, native multimodality, and agentic reasoning, built on their Sparse Attention architecture. Try it in Atomic Chat
-
Agents need memory before tools, not expensive goldfish
By
–
We gave agents tools before we gave them memory.
— God of Prompt (@godofprompt) 1 juin 2026
That was backwards.
Now they can browse, code, email, book meetings, hit APIs…
…but still wake up tomorrow with no idea what they learned yesterday.
That is not an agent stack. That is a very expensive goldfish with… https://t.co/k1DqTtViOb pic.twitter.com/vH1kBgbqNtWe gave agents tools before we gave them memory. That was backwards. Now they can browse, code, email, book meetings, hit APIs… …but still wake up tomorrow with no idea what they learned yesterday. That is not an agent stack. That is a very expensive goldfish with
-
Codex working nonstop since 11am, feels like an AI employee
By
–
I launched Codex on a goal at 11am, it's 5pm and it's still working. I've never felt so strongly the feeling of having an AI working for me. Like, it's doing a normal workday right now. I'm working on something else while it…