#llm

Articles tagged with #llm

I wrote a profiling tool for agents
While building an agent for a client, we hit a scaling problem: a coordinator agent had 4-5 subagents each with 15-20 tool calls. Each tool result got appended to the context, then what started as a r
Apr 9, 20262 min read114
If I could turn back time
Have you ever exclaimed after a few hours engaged in some fruitless activity, "Well, that's X hours of my life I'll never get back"? Or, when in a reflective mood, "I wish I knew this when I was 16!"?
Feb 19, 20263 min read180
Your evals have a Rotten Tomatoes problem
You push a change to a prompt and your eval score drops from 0.91 to 0.84. Something got worse, but the score doesn’t tell you what. So you start re-running the pipeline, tweaking your inputs, pouring
Feb 12, 20268 min read396
Tiny OCR
0.9B parameter model running on CPU matched a 50¢/M token cloud API
Feb 11, 20263 min read182
On the new larger context windows
Today the latest LLMs have large context windows up to ~1 million tokens. There are many occasions when this larger context window can be useful: Context engineering: injecting rich system/user conte
Nov 4, 20252 min read335
Your Questions on Building with AI
Since the launch of Airbyte 1.0 with AI Assist, hundreds of new Airbyte connectors have been built. We recently joined our partners at Airbyte for the Data Bytes meetup where we answered questions from an audience of data engineers, AI enthusiasts, a...
Nov 13, 20247 min read262