Looks like they recently landed a PR fixing that https://
github.com/BerriAI/litell
m/pull/26157
…
LLMS
-
LiteLLM Fixes Bug with Recent Pull Request Merge
By
–
-
Talkie: New Vintage Language Model Trained on Historical Pre-1931 English
By
–
Some notes on talkie, a new "vintage language model" from a team including Alec Radford (yes, that Alec Radford) "trained on 260B tokens of historical pre-1931 English text"
-
Conductor Framework Orchestrates AI Agents Using Natural Language
By
–
Learning to Orchestrate Agents in Natural Language with the Conductor Fugu Blog: https://
sakana.ai/fugu-beta
Paper: https://
arxiv.org/abs/2512.04388 -
OpenAI’s Realtime API Demonstrates Fast Speech Recognition and Function Calling
By
–
The Realtime API is fast.
— Romain Huet (@romainhuet) 28 avril 2026
This demo by @jxnlco is running at real speed! No computer use, just realtime speech + function calling.
The model is listening, deciding when to call functions to update state, and yes, it doesn’t always have to talk back! https://t.co/2cK4jzI7rIThe Realtime API is fast. This demo by @jxnlco is running at real speed! No computer use, just realtime speech + function calling. The model is listening, deciding when to call functions to update state, and yes, it doesn’t always have to talk back!
-
DeepSeek v4 Now Supports Fill-in-the-Middle Capability
By
–
Also the new @deepseek_ai v4 supports FIM now! 😀 (Requires using the beta header.)
-
OpenClaw Agent Runs on talkie-1930-13b-base Model
By
–
"Yeah, my OpenClaw runs entirely on talkie-1930-13b-base, I connect to it only through telegram. No, not that telegram."
-
Vintage LLM Runs on Device: Pre-1931 Siri Era
By
–
The new LLM trained only on pre-1931 text is small enough that it can potentially run on device, so, with the right tools, you can get a fully vintage version of Siri, but from the era of Downton Abbey. Here, I asked for it to arrange for sushi delivery in Philadelphia. Hmmm…
-
LiteLLM Critical Issue Forces Downgrade Other Packages
By
–
I know the litellm team have a *lot* going on, & I have no desire to increase their workload even more… But if you're a litellm user, this is a critical issue to know about – it currently force downgrades your other packages if you use a recent version:
-
Claude Opus outperforms ChatGPT and Gemini on deck design task
By
–
Just gave Claude (Opus 4.7 and Sonnet 4.6), ChatGPT 5.5, and Gemini 3.1 the same prompt to build a deck design. Gemini & ChatGPT outputs were intern-level at best. Claude was senior designer. Crushed it. Not surprised. Kept prompt simple: “I’d like to create a slide template
-
AI Model Knowledge Cutoff and Scientific Bias Analysis
By
–
This is an incredibly cool experiment
— Ethan Mollick (@emollick) 28 avril 2026
It is also fascinating that the model knows information up to 1931, but, at least in some science topics, seems very stuck in the early 1900s. For example, it defends the lumiferous aether hypothesis & has a distrust of special relativity https://t.co/xTVF7tkIw8 pic.twitter.com/UvcUFuJb90This is an incredibly cool experiment It is also fascinating that the model knows information up to 1931, but, at least in some science topics, seems very stuck in the early 1900s. For example, it defends the lumiferous aether hypothesis & has a distrust of special relativity