Its also a shame because Google has some of the most innovative AI apps, like NotebookLM, but they need smarter brains to power them (as well as the harnesses needed for those brains)
LLMS
-
LFM2.5-ColBERT-350M reliably selects top 5 tools from 151
By
–
LFM2.5-ColBERT-350M is a surprisingly reliable smart tool selector.
— Maxime Labonne (@maximelabonne) 18 juin 2026
We gave it 151 tools, and it consistently surfaces the 5 most relevant ones based on the user prompt.
This saves tokens and improves accuracy. Ideal for hmmmm agentic edge models? 👀 pic.twitter.com/IPyizctesULFM2.5-ColBERT-350M is a surprisingly reliable smart tool selector. We gave it 151 tools, and it consistently surfaces the 5 most relevant ones based on the user prompt. This saves tokens and improves accuracy. Ideal for hmmmm agentic edge models?
-
Google lacks public frontier model, Gemini 3.1 Pro lagging
By
–
Interestingly, Google no longer has a public frontier model. They have a very good flash model, but a very good flash model can't do frontier work without a good frontier orchestrator. I am sure this will change soon, but Gemini 3.1 Pro is very clearly lagging at this point.
-
Causal decoder patched to bidirectional encoder excels in multilingual tasks
By
–
We patched LFM2.5-350M (pre-trained on 28T tokens) to transform a causal decoder into a bidirectional encoder. It worked extremely well: both Embedding and ColBERT models get best-in-class performance, especially for multi/cross-lingual tasks.
-
GLM-5.2: best open-weight model with multi-head latent attention
By
–
Just updated with the recent release of GLM-5.2. The best open-weight model today. Architecture-wise, it is built on the GLM-5 and GLM-5.1 architecture that I covered previously, meaning it reuses the Multi-head Latent Attention mechanisms.
-
V can join memory channels and run code
By
–
V can join channels with memory of past tasks and goals, write and execute its own code, and turn conversations into completed tasks. Documented
-
Any LLM can run on Codex, not just OpenAI
By
–
WHAAAT?! TIL you can run any LLM on Codex A lot of devs (including me!) still thought Codex was completely locked into OpenAI's ecosystem. It isn’t. You can completely bypass the default models and run the exact stack you want for your workflow. Here is what the routing
-
Post sharing links to Deepeval and LangChain
By
–
Docs: https://
deepeval.com/integrations/f
rameworks/langchain#in-cicd-pytest
… GitHub Repo: https://
github.com/confident-ai/d
eepeval
… -
Pytest for AI Agents: Testing LangChain chains locally
By
–
Pytest for AI Agents! (100% open-source and runs locally) Building agents with LangChain means chaining LLMs, tools, and retrieval steps together. Each component can fail differently. The output changes with every run. Traditional unit tests don't work here because there's no