Filip Procházka (@prochazkafilip) 's Twitter Profile
Filip Procházka

@prochazkafilip

Backend ⚡ Java/Kotlin, PostgreSQL, Cloud. 🛠️ Recovering overengineer.

ID: 37413851

linkhttps://filip-prochazka.com calendar_today03-05-2009 13:09:09

28,28K Tweet

2,2K Followers

542 Following

Filip Procházka (@prochazkafilip) 's Twitter Profile Photo

I never liked GraphQL, but having a very dynamic "endpoint" where you can query only what you need actually sounds like a sweet spot for MCP tools and LLMs in general 🤔 apollographql.com/blog/the-futur…

kepano (@kepano) 's Twitter Profile Photo

OpenAI is now required by court order to preserve all ChatGPT logs including "temporary chats" and API requests that would have been deleted if I understand this correctly, it means data retention policies for apps that use OpenAI API simply cannot be honored

OpenAI is now required by court order to preserve all ChatGPT logs including "temporary chats" and API requests that would have been deleted 

if I understand this correctly, it means data retention policies for apps that use OpenAI API simply cannot be honored
Jake (@justjake) 's Twitter Profile Photo

Called shot: AI will help software engineers become product managers faster than product managers becoming software engineers

Filip Procházka (@prochazkafilip) 's Twitter Profile Photo

There is a great community meetup happening next week in Brno - it's always well organized, and the people there are very friendly. Don't hesitate to register, you'll definitely learn something new! meetup.com/kotlin-server-…

Ruben Hassid (@rubenhssd) 's Twitter Profile Photo

While AI companies celebrate their models "thinking," Apple basically said "Everyone's celebrating fake reasoning." The industry is chasing metrics that don't measure actual intelligence.

Jan Honza Černý (a.k.a. chemiX) (@janhonzacerny) 's Twitter Profile Photo

Před prázdnináma ještě jedno AI4DEV → v Praze a bude to jízda; Souki Petr Soukup a Lukáš z 2FRESH s inpirativní přednáškou a pak nezřízená diskuze, co a jak dál... meetup.com/ai-4-dev/event…

Filip Procházka (@prochazkafilip) 's Twitter Profile Photo

Semi-related: This is why I love the ADR format. It forces you to write down the context of the decision, therefore allowing to easily challenge it later, when the initial reason for the rule goes away.

Alex Vacca (@itsalexvacca) 's Twitter Profile Photo

The solution isn't to ban AI. It's to use it strategically. The choice is yours: Build cognitive debt and become an AI dependent. Or build cognitive strength and become an AI multiplier. The first brain scan study of AI users just showed us the stakes. Choose wisely.

The solution isn't to ban AI. It's to use it strategically.

The choice is yours:
Build cognitive debt and become an AI dependent.
Or build cognitive strength and become an AI multiplier.

The first brain scan study of AI users just showed us the stakes.

Choose wisely.
Theodora Chu (@chu_onthis) 's Twitter Profile Photo

new mcp spec just dropped: 1. auth is fixed! at last! 2. elicitation now makes it possible for a server to ask an end-user for more info, enabling more agentic behaviors 3. structured tool outputs makes it easier to reason about tool responses 4. more security documentation

Neil (@irl_neil) 's Twitter Profile Photo

Obviously using chatbots makes you more dumb, everyone is skipping over the funniest part: the study authors are such dedicated LLM haters they set up traps to expose AI users lol

Obviously using chatbots makes you more dumb, everyone is skipping over the funniest part: the study authors are such dedicated LLM haters they set up traps to expose AI users lol