Read more about LinkedIn’s SQL Bot https://
linkedin.com/blog/engineeri
ng/ai/practical-text-to-sql-for-data-analytics
…
LLMS
-
LinkedIn’s SQL Bot: Practical Text-to-SQL for Data Analytics
By
–
-
o3 refers to itself as ‘We’ and ‘Our’ in outputs and Chains of Thought
By
–
o3 refers to itself as "We" and "Our" in outputs and Chains of Thought.
-
OpenAI ChatGPT memory upgrade recalls old conversations you didn’t save
By
–
“Facts” “OpenAI is giving ChatGPT a memory upgrade that allows it to recall old conversations that you didn’t ask it to save.”
-
OpenAI Releases GPT-4.1 API, Introduces o3 and o4-mini Models
By
–
Here's the AI News I came across this week (it's a lot) – What have I missed? – OpenAI releases GPT‑4.1 in API
– OpenAI introduces o3 and o4‑mini models
– OpenAI adds image gallery in ChatGPT
– OpenAI plans to retire GPT‑4 model soon
– OpenAI will sunset massive GPT‑4.5 model
– -
Cell2Sentence-Scale: Language Models for Single-Cell Analysis
By
–
Today on the blog we introduce Cell2Sentence-Scale, which looks deep into how to best represent cells and biological information as text, opening up exciting applications for language-driven single-cell analysis with large language models. Learn more →
https://
goo.gle/4jC24dM -
Model Thinking Budget Billing Mechanism Update
By
–
In some rare cases, the model still thinks a little even with thinking budget = 0, we are hoping to fix this before we make this model stable and you won't be billed for thinking. The thinking budget = 0 is what triggers the billing switch.
-
Extended Thinking Output Tokens Charged at Standard Rate
By
–
When you have thinking turned on, all output tokens (including thoughts) are charged at the $3.50 / 1M rate
-
Summarization Feature Explored for General Availability Launch
By
–
We are exploring summarization, on the list for GA!
-
Claude 2.5 Flash Coding Progress Accelerates Significantly
By
–
2.5 flash coding progress is super strong! And much more to come still 🙂
-
Claude 2.5 Migration Strategy: Reasoning vs Non-Reasoning Trade-offs
By
–
Trying to give developers on 2.0 flash a clean migration path to 2.5, which meant we had to do a trade off somewhere, in this case we split reasoning vs non-reasoning as that balance, but open to feedback!