MolSoft LLC & XtalPi Inc. Partner to Integrate CombiRIDGE™ with the VAST™ Chemical Universe We are excited to announce a strategic partnership between MolSoft LLC and XtalPi, an end-to-end workflow that bridges ultra-large-scale 3D VS molsoft.com/news.html

Vance says that stopping funding for Ukraine is one of his proudest achievements in this administration. ​I’m watching this stunningly cruel speech from Ukraine, as Russia continues to kills us every day. Just today, they killed 8-year-old boy in Cherkasy and five people in Dnipro. Dozens more were injured. ​The military assistance you are so proud of stopping was used to save lives in a war Russia started and continues every day by choice, in a war that only became possible after USA pressured Ukraine into disarming... ​I do not know if Vance can fully comprehend the scale of the tragedy unfolding here: a brutal, illegal war of extermination by Russia, and the slow abandonment by our allies. There is nothing to be proud of. Absolutely nothing.

llm agents sessions are clearly now part of the work product itself, and it's strange that products have not caught up. @ashot's codecast is a solid 6 months ahead of the curve here

Next evolution of coding agents will include proactivity. monitor x and perform y

turns out starcraft is the best base for the new age of software engineering

As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently: "openai/gpt-5.1", "google/gemini-3-pro-preview", "anthropic/claude-sonnet-4.5", "x-ai/grok-4", Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response. It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses. Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain. That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored. I pushed the vibe coded app to github.com/karpathy/llm-coun… if others would like to play. ty nano banana pro for fun header image for the repo

When using a coding (or other agent) the trick many times is not to give it all the context it needs manually in the prompt, but come up with a task for it to do that will have it build the right context for itself.

We need shared spaces for agent conversations, and to include and save these convos as artifacts connected to the code itself.

github.com/ashot/gh-pr-comme… install and pair with slash command: gist.github.com/ashot/327e13… for better agentic code reviews

This is a beautifully crafted screen recorder (#1 Product of the Day), made by one of my fav creators 👇

We are close to the holy grail here, an automated process of self improvement from production data.

There's a missing social vibecoding app: ideate, create, host, remix and collaborate

This actually gives me some hope that Trump will reconsider his tariff plans. Low oil prices hurt Russia, and he never seems to do anything contrary to Russia's interests.

feeling the AGI today

One thing I don't see being discussed enough is that there are limits to intelligence itself. How much more rational or well reasoned can one be? We may be pushing up against universal/physical barriers rather than limits of a particular approach (LLMs)

AI coding agents need ability to choose to jump back (and undo code changes) on their own (this didn't work, let me back up), and to build up a condensed understanding of the tree they have explored so far

Russia cannot defeat Ukraine or the West – and will likely lose - if the West mobilizes its resources to resist the Kremlin. That the war is unwinnable due to Russia’s dominance is a Kremlin information operation & a glimpse into Russia's real strategy & only hope of success.🧵