Dariusz Debowczyk @ddebowczyk

I build Instructor: LLM outputs → dev-friendly, validated data objects // Thoughts on #automation #llm #dspy #textgrad #php #python // Check Github repo 👇 instructorphp.com Warsaw Joined January 2011

Tweets

4K
Followers

773
Following

2K
Likes

714

Dariusz Debowczyk @ddebowczyk

4 days ago

Instructor for PHP v1.5.0 has been released with cleaner, modularized code, more fixed bugs, refreshed docs, and more. Developer friendly, framework agnostic way to get structured data from LLM outputs. github.com/cognesy/instru…

0 0 4 960 1

shyamal @shyamalanadkat

3 weeks ago

the future is more engineers using AI to ship 10x, not fewer because of AI.

9 4 67 5K 4

Dariusz Debowczyk @ddebowczyk

2 months ago

InstructorPHP v1.0.0 released! 🎉 First stable release of InstructorPHP - MIT/OS library for structured data extraction and LLM integration for PHP apps. Framework agnostic, batteries included. 🔥 StructuredOutput, Inference, and Embeddings classes with fluent, cohesive APIs.…

0 1 5 1K 0

Download Image

Rohan Paul @rohanpaul_ai

3 months ago

A 340 page huge report on AI trends - released by @bondcap Some wild findings from this report. 🧵1/n

45 112 591 137K 1K

Download Image

Kasey Zhang @_WEEXIAO

3 months ago

Don't use structured output mode for reasoning tasks. We’re open sourcing Osmosis-Structure-0.6B: an extremely small model that can turn any unstructured data into any format (e.g. JSON schema). Use it with any model - download and blog below!

92 199 2K 301K 3K

Download Gif

Dariusz Debowczyk @ddebowczyk

4 months ago

2025.1 versions of Jetbrains IDEs (Pycharm, PhpStorm) are working super slow on my machine. Does anybody experience similar issue?

0 0 1 87 0

Dariusz Debowczyk @ddebowczyk

4 months ago

Version 1.0 of Instructor for PHP is coming with **many** breaking changes. Multiple APIs from 0.x have been remodelled. If you're using Instructor in production and we haven't spoken yet, please ping me via DM. I'd like to discuss the best way to roll it out to limit the…

0 0 5 835 1

Dariusz Debowczyk @ddebowczyk

4 months ago

Context synthesis to fork existing chat is difficult as it relies on understanding of a broader context, eg user goals or constraints which may not be explicitly stated in the data sources. It may have to be proceeded with another step / steps to discover user's intent behind…

BURKOV @burkov

4 months ago

41 17 225 11K 49

0 0 0 119 0

Dariusz Debowczyk @ddebowczyk

4 months ago

Code reuse isn't free. Nor is building everything from scratch.

Steren @steren

4 months ago

Code reuse isn't free. Nor is building everything from scratch.

49 12 450 247K 278

Download Image

0 0 1 103 0

Dariusz Debowczyk @ddebowczyk

4 months ago

I love the simplicity of "just putting it into context" - and it may work for some scenarios. But for majority of non trivial use cases information retrieval, context synthesis and context window management steps will stay with us (in some form).

Agent B @MichelIvan92347

4 months ago

0 0 0 184 1

1 0 3 122 0

elvis @omarsar0

4 months ago

The paper investigates how LLMs perform in realistic, multi-turn conversational settings where user instructions are often underspecified and clarified over several turns. I keep telling devs to spend time preparing those initial instructions. Prompt engineering is important.