A senior Google engineer just dropped a 19-page PDF on "Loop Engineering" for LLM and agentic systems.
Act → Observe → Learn → Repeat
• Act: the LLM proposes a code transformation (tile this loop, parallelize that one).
• Observe: a compiler runs it and reports back - is it valid? faster? slower? by how much?
• Learn: the LLM reads that feedback and adjusts its next move.
• Repeat until it stops finding improvements.
The agent gets smarter purely from grounded feedback inside its own context window.
This 19-page PDF totally changed the way I’m building agentic systems today.
Read it now, then explore the article below.
@RaphaelDabadie I’ve been working on that topic and giving workshops to Van Cleef, EDF, Cofidis and many big names. I wrote a training with my feedback from the field, happy to talk about it if you’re interested!
@marcel_binz@Nature Hello! I fell in love with this project!! I would love to build on top of it: I have plenty of ideas but I don't know if I could make myself useful by working on a specific topic to help? I have a Bachelor's degree in cognitive neuroscience and 5+ years as a data scientist.
Quite surprised there’s no mention of their IPO here. As @Bendini_Lambert stated: Anthropic’s running against the clock here, and probably trying too hard (preventing competitors from using their public models for frontier AI research, shady pricing…)
I’ve had a number of conversations with folks inside and outside government about the current situation with Anthropic, and here is what I believe to be true:
— As we know, Anthropic publicly released its Mythos class models earlier this week under the commercial name Fable.
— Fable is Mythos with guardrails. But if those guardrails fail, then you’ve exposed Mythos and its advanced cyber capabilities to people who shouldn’t have them. (Keep in mind that Anthropic itself widely promoted the idea that Mythos was a cyberweapon and needed to be regulated as such. They asked for government regulation of Mythos and championed the guardrails on Fable. If there is a vulnerability — big or small — it is Anthropic’s responsibility to patch.)
— A highly credible trusted partner of both Anthropic and the USG who was testing Fable came forward with a jailbreak of those guardrails. The Admin asked Dario to fix the jailbreak or de-deploy the model. Dario refused.
— In their blog post, Anthropic defended its decision by saying the jailbreak isn’t serious. That is not what the trusted partner and the USG believe; nor is that kind of minimizing language consistent with Anthropic’s brand as the AI safety company. It’s difficult to fathom how they could claim a jailbreak allowing operability of a cyber weapon could be defined as not “serious.”
— In the past, Anthropic has always said that safety must be top priority and taken super seriously. In this case, Anthropic prioritized the continued offering of the consumer model over safety.
— In reaction, the Admin issued the export control. The Admin did this reluctantly. It’s been very surprised that Anthropic hasn’t wanted to cooperate with a reasonable safety request (ie fixing the jailbreak issue). Anthropic’s reaction is very much at odds with their branding and ethos as a safe AI research community.
— The Admin’s hope now is that Anthropic remediates the safety issue, the export control is lifted, and Fable goes back into general release. The Admin wants all of this to happen as soon as possible. It is frankly bewildered that Anthropic hasn’t wanted to comply with safety requests that it previously said were its highest priority.
— Those trying to misdirect and tie this action to the prior DoW/Anthropic issues are wrong. The Admin values Anthropic’s technical capabilities and feels that this issue, while serious, should be easily resolved. The ball is in Anthropic’s court.
big news! 🥳 got into YC solo founder with $40k monthly revenue!
building Thomas: the first YC-backed AI founder (yep, we cloned myself)
Thomas is a virtual human who starts, runs, and grows his own companies. His only goal is to make money. Once launched, he works forever toward that goal.
More info in the first comment!
And about YC: just as wonderful as I expected, very lucky to have @dessaigne and @collinmathilde as partners.
More soon 🙌🥳
For everyone asking why this is such a big deal and why I think marks the beginning of a new era of scientific discovery — I wrote it all here:
https://t.co/ZaZC8H8eWi