agent observability is great. but in order to use it to power an agent improvement loop, you need to be collecting (and even generating) feedback data inside your agent observability platform
LLMS
-
GPT-5 Derives New Results in Theoretical Physics and Quantum Gravity
By
–
🔬Doing Vibe Physics
— Latent.Space (@latentspacepod) 5 mai 2026
The full story of how GPT‑5.x derived new results in theoretical physics and quantum gravity, live on our Science pod today! https://t.co/EVj2tITVGJ
our conversation with @ALupsasca, an award winning theoretical physicist on his AGI-pilling journey… https://t.co/O2Y2SQwtzn pic.twitter.com/vs5q1WoXGoDoing Vibe Physics The full story of how GPT‑5.x derived new results in theoretical physics and quantum gravity, live on our Science pod today! https://
latent.space/p/lupsasca our conversation with @ALupsasca
, an award winning theoretical physicist on his AGI-pilling journey -
GPT-5.5 Instant Major ChatGPT Upgrade Rolling Out Now
By
–
Major ChatGPT upgrade rolling out now, in the form of GPT-5.5 Instant: https://t.co/QG7pQHwFja
— Greg Brockman (@gdb) 5 mai 2026Major ChatGPT upgrade rolling out now, in the form of GPT-5.5 Instant:
-
Anthropic Model Spec Midtraining Study and Alignment Research
By
–
Read more about Model Spec Midtraining: https://
alignment.anthropic.com/2026/msm Or read the full study: https://
arxiv.org/abs/2605.02087 -
Model Specs and Constitutions Drive Better AI Alignment Generalization
By
–
Using MSM, we can also empirically study which model specs or constitutions yield the best generalization from alignment training. Specifying rules works to some extent, but explaining the values underlying those rules (or adding more detailed subrules) is even better.
-
MSM Training Reduces Unsafe Agentic Actions in AI Chatbots
By
–
A more realistic example: AIs trained to be harmless chatbots can take unsafe actions in agentic settings. Preceding this training with MSM on a realistic spec drastically improves generalization, reducing unsafe agentic actions.
-
MSM Training Teaches AIs Their Behavioral Spec for Better Alignment
By
–
Developers try to align AIs to a constitution, or spec, describing intended AI behavior. But AIs don’t normally know what’s in it. MSM adds a training phase for teaching an AI about its spec. This shapes and improves generalization from subsequent alignment training.
-
MSM Technique Transfers Broad Values from Minimal AI Training
By
–
A toy example: Train an AI only to say it likes certain cheeses. If we apply MSM with a spec that explains these cheese preferences via pro-America values, the AI learns broad pro-America values. Swap to a pro-affordability spec? The AI learns to value affordability instead.
-
Anthropic Introduces Model Spec Midtraining for Better AI Alignment
By
–
New Anthropic Fellows research: Model Spec Midtraining (MSM). Standard alignment methods train AIs on examples of desired behavior. But this can fail to generalize to new situations. MSM addresses this by first teaching AIs how we would like them to generalize and why.
-
AI Improvements in Speed, Intelligence, Personality, and Memory
By
–
in particular, the combination of improvements to speed, intelligence, personality, and great memory/personalization feels like a more-than-sum-of-the-parts thing when it all hits together