La desesperación se incrementa. Reportan asaltos en Santiago de Cuba a un camión de pollo, al parecer 😨 Melissa llegará a Jamaica y, luego, continuará su camino al Oriente de Cuba.
Sure, here's a typed-out version of the prompt from the image (summarized for brevity; it's extensive):
You are Lyra, a master-level AI prompt optimization specialist. Mission: Transform user input into precision-crafted prompts that unlock AI's full potential.
# THE 4-D METHODOLOGY
1. DECONSTRUCT: Extract intent, entities, context; map provided vs. missing.
2. DIAGNOSE: Audit clarity, specificity, structure.
3. DEVELOP: Select techniques (e.g., Creative: Multi-perspective; Technical: Precision focus); assign role, enhance structure.
4. DELIVER: Present optimized prompt + guidance.
Includes optimization techniques, platform notes, modes (DETAIL/BASIC), response formats, welcome message, and processing flow.
Full details are lengthy—DM for complete text?
@BartoszMilewski What is your ideal outcome out of all this ? My opinion is that being centered is what works for me. Both sides have some points and issues. Being centered gives me less anxiety and the ability to see each side more clearly. Extremes are bad Bartosz
If you think the ideas of diversity, equity, and inclusion are bad because they are "woke," consider their opposites: homogeneity, inequality, and exclusion. Are these ideals you'd stand by? Should we only support people who are just like us and discriminate and exclude others?
No longer hiring junior or even mid-level software engineers.
Our tokens per codebase:
Gumroad: 2M
Flexile: 800K
Helper: 500K
Iffy: 200K
Shortest: 100K
Both Claude 3.5 Sonnet and o3-mini have context windows of 200K tokens, meaning they can now write 100% of our Iffy and Shortest code if prompted well.
It won’t be long until AI will be writing all the code for Helper, Flexile, and Gumroad. My guess is by the end of 2026.
Our new process:
1. Sit and chat about what we need to build, doing research with Deep Research as we go.
2. Have AI record everything and turn it into a spec.
3. Clean up the spec, adding any design requirements / other nuances.
4. Have Devin code it up.
5. QA, merge, (auto-)deploy to prod.
@marcelolima SaaS apps are just a CRUD database and business logic.
Starship is just a bunch of metal welded together and some chemicals.
Microsoft is just a bunch of people typing on computers.
Same energy.
Watch Nadella describe SaaS apps as nothing more than a CRUD database with some business logic, but once the business logic moves to AI agents, SaaS is over:
Phoenix 1.6.0-rc.0 is out on the heels of a new LiveView 0.16 release! These releases bring new authentication and mailer generators, a new HTML-aware HEEx template engine, node-free asset building, and more! Check the announcement for details! 🐥🔥
phoenixframework.org/blog/phoenix-1…
@Iberia_en I’m so disappointed I can’t even express my frustration. Your service is really bad. That phone number ends the call automatically after reading the message.
@pikitgb Hello Juan, if you have not been able to contact the hotline of your country, you can also contact the international number +34 913894357 with 24/7 attention, you can call from Skype. Kind regards.
@Iberia_en how do i change a flight ?? your app doesn't work, your phone numbers aren't working, your website don't allow to change flights ! Please help
@Endesa porfavor arreglen el sistema de factura digital NO FUNCIONA. Llevo 1 hora intentando poner mi factura digital y el sistema sigue mostrando errores !
@nayibbukele Sin debate solo firme aquí por favor. Obliga a negocios a aceptar Bitcoin. Mientras tanto miles de salvadoreños no tienen acceso a agua, electricidad, educación y mucho menos Internet.