“Study hard what interests you the most in the most undisciplined, irreverent and original manner possible.”
― Richard Feynmann
I am currently studying:
ralph wiggum, rlms, dspy, gastown & related agent orchestrators, agent-native apps and orgs
How about you?
is it a good thing or a bad thing that it took opus 5.5 about 30 minutes to clone my writing from my blog?
maybe it is just a thing. an interesting thing...
...still not sure if a useful thing.
in case you were curious: fable 5.2 and I confirmed that if you record yourself singing and whistling every note in your range, you can play basically any song using only your voice
no song is playing in this video. every sound is one of 64 clips of me holding a single note
UI inputs have always been strict: they force you to give an exact answer.
That's bc the code behind them couldn't handle anything *fuzzy*, even though people think in "around" and "ideally."
But your agents can. So what if they hand you the controls that let you answer roughly? <fuzzy ui>
What if fine-tuning took a paragraph and a few seconds?
We trained a meta-model that writes the weight update for Qwen3.5-2B from a one-paragraph task description, in seconds on one small GPU, no gradient step.
Across 75 public benchmarks, the update written from just one paragraph improved the base model's score on 59 of them and lowered it on 8. For example, ComVE jumped from 50.0 to 91.1 percent, three-object logical deduction went from 46.4 to 82.0, and on GSM8K with the final number only, from 5.7 to 18.6, ahead of a LoRA trained on up to 1,400 rows of GSM8K (12.7).
Post, figures and every benchmark: roicohen.org/blog/compress-b…
There is a developing situation with some U.S. banks. This is not yet confirmed as a cyberattack. But it does seem to be spreading. It started with Chase and Bank of America and now Wells Fargo, Zelle, Capital One, and U.S. Bank are also reporting issues. Logins are down on both web and app, and even some ATMs have stopped working. Transfers are down, and some accounts are showing zero balances.
There is no official explanation or statement from any of the affected banks yet. There is nothing confirmed that says this is serious yet or has anything to do with AI or hacking. If it develops beyond this point, I will make a thread.
one of the most brilliant takes i've seen as of late on HCI in the era of LLMs
Attention steering by Sun Chuanqi. Actually operating an LLM's attention and token generation. the concept, UX and sound design are just amazing. There are still so many unexplored patterns. this one's particularly inspiring
github.com/chuanqisun/spaces…
We trained an open model to do weight-space programming.
@thinkymachines’ Inkling 2 Small, post-trained on @tinkerapi, repairs broken networks from their raw weights in ~40 tokens, no reasoning. In the tokens it needed untrained to fix one, it now answers 207 and repairs 176.
Want to try weight-space programming? Today we're releasing dspy-wsp, a prototype weight-space optimizer that works like any other @DSPyOSS optimizer.
Using dspy-wsp, and about ~$5-10 of Astra, we improved every decision model we tested. cmpnd.ai/blog/weight-space-p…
This whole thing sucks, and I wish none of it had happened. It’s a really sad day!
But I want to make one thing clear: we’ll keep fighting for open-source AI, harder than ever. This is too important to slow down now. Let’s go!
🚀 Today we're launching Agent Sandboxes in @pydantic Logfire: a profoundly different kind of sandbox.
"The world doesn't need another sandbox" they say. Maybe. Or maybe the world doesn't need another firecracker/gVisor/VM infra-fest.
Our Agent Sandboxes are different. They're just an isolated interpreter with cold start times measured in milliseconds, where the code can only call the tools you give it and use the directories you mount.
A massive bonus is you can snapshot and resume a REPL weeks later, with the snapshots costing virtually nothing.
Programmatic tool calling, solved.
Start free, $1000 of free credit to try it in the first month 👇
pydantic.io/launch-agent-san…