AI systems and performance @ https://xitter.cf/t.co/q5IUJ7AMI9
San Francisco, CA
Joined July 2012
- Tweets364
- Following2.3K
- Followers1.5K
- Likes278K
Cade Daniel 🇺🇸 retweeted
Yes, it's true. After years working as a researcher in the field of AI, my jumpshot is finally on camera. And @oneill_c beat me in a friendly game of HORSE. or did he?....
(also thanks to BaseTen for letting me keep the ball, along with many bags of Cheez-Its)
AI researchers' idea of a good time: playing HORSE and debating continual learning between shots.
@oneill_c (co-head of training at Baseten) and @jxmnop (co-founder and head of research at @EngramLab) discuss:
- when to put knowledge in weights vs. the KV cache,
- why forgetting matters less for specialized models,
- on-policy self-distillation vs. RL, and
- what research publishing should look like today.
Watch the full game (and discussion) here: youtu.be/q_-_t5AmKz0
Work from @EngramLab on study compute reducing inference tokens while simultaneously increasing their quality👇
Cade Daniel 🇺🇸 retweeted
In collaboration with @harvey, we’re excited to build a new kind of agent environment to reflect realistic knowledge work: an entire synthetic law firm, Calderwood & Harkness, with over 100M (!) tokens of documents and 250 client cases. 💼
Today’s AI models know a lot about the law, but don’t understand how the law is practiced, because this information remains proprietary within firms. Unlike how agents are benchmarked today – starting each task from scratch with a new set of context — lawyers accumulate knowledge over time, building on years of experience.
Calderwood & Harkness makes it possible for agents to do the same. Legal agents do many tasks in the same environment, making it possible to leverage memory and experience to do better work over time.
We’ve had a great time co-developing this benchmark with Harvey’s research team, partnering @ItsJulioPereyra @nikogrupen @gabepereyra. We’ll share more results on this soon.
RT @harvey: We're open sourcing a 100M+ token synthetic law firm we built with @EngramLab.
The firm contains work product from 250+ synthe…
This quoted post is unavailable.
Cade Daniel 🇺🇸 retweeted
the longevity of the DSV3 architecture should be an update to anyone whose world model hinges on unbounded algorithmic progress via recursive self-improvement
Cade Daniel 🇺🇸 retweeted
Thrilled for my friend @dan_biderman to launch @EngramLab
Dan is a visionary who has consistently let seen around corners in AI
Cade Daniel 🇺🇸 retweeted
I'm really excited to be working with Engram to bring their models into Custom Agents in Notion. There's something magical that happens when the agent stops needing to search your workspace, and just knows it.
Cade Daniel 🇺🇸 retweeted
this is insanely cool. engram is pretty much working on a model that can improve itself through every interaction across *all* users
which will likely be the single biggest capabilities jump since o1-style chain of thought reasoning
Cade Daniel 🇺🇸 retweeted
Now that Tacit Labs and Engram are out of stealth, a casual plug for interning on the research team at @databricks:
* @ninklefitz → Founder @tacitlabsco
* @lindensli → Founder @appliedcompute
* @dan_biderman → Founder @EngramLab
* @ChrisRinard → Founder @Standard_Kernel
RT @simran_s_arora: So thrilled for @EngramLab, working on such an important problem!!! Had the pleasure of working closely with @EyubogluS…
This quoted post is unavailable.
Cade Daniel 🇺🇸 retweeted
Have been excited about this team for a long time! Memory is one of the next big unlocks in AI. Thrilled to partner with this exceptional group @dan_biderman, @EyubogluSabri, @realJessyLin, @jxmnop, @scott_linderman, and Chris.
There will be many new internet-scale datasets, created by agents
Agents will exponentiate the amount of data that exists in the world. Most are focused on building agents, @dan_biderman and the @EngramLab team are one of the few groups thinking about what happens to knowledge work when it is agent-led.
Congrats to them on the launch and pumped to continue working together on scaling compute for knowledge work.
Cade Daniel 🇺🇸 retweeted
Engram is the bitter lesson applied to context.
Whenever people ask me about the coolest under the radar companies I tell them about Dan. No longer under the radar, very excited for @dan_biderman and co to be sharing Engram with the world!
I've joined Engram!
Our thesis starts with the observation: today's AI systems are brilliant strangers. Every new chat requires re-establishing your context. Memory systems help, but we believe the market-defining solution will be to encode memory directly into the model itself. That creates a new scaling axis: scaling compute on context.
The team is amazingly talented, and we're working with outstanding large-scale partners such as Microsoft, Harvey, and Notion.
If you're interested in RL infrastructure, Cartridges and LoRA, or pushing the limits of per-user training and serving performance at trillion-parameter scale, we'd love to hear from you.
Cade Daniel 🇺🇸 retweeted
What if we could teach LLMs to be algorithm inventors?
I trained an LLM to improve sorting algorithms through pure reinforcement learning - and it discovered optimizations giving 47.92x speedups over an optimized python based Timsort baseline! No cold-start data needed.
I used @huggingface grpo implementation and @Alibaba_Qwen 7b model.
