Senior Software Engineer. Pokemon Fan. Building https://teapawt.net/t.co/B2h43hI8PB for the fun of it! 🇵🇷
San Juan, Puerto Rico
Joined October 2025
- Tweets437
- Following404
- Followers146
- Likes1.7K
AMANSA retweeted
#PokémonPocket : Aperçu global de toutes les cartes de l'extension Fusion Double qui débarque demain !
AMANSA retweeted
Este mazo de Miraidon EX está rotísimo, sin duda el mejor que he jugado esta temporada de rankeds.
Tenéis el mazo en el video de hoy 👇
youtu.be/ry1mQz6EbK0
AMANSA retweeted
Serebii Update: First look at the Special Pack - First Partners in Pokémon TCG Pocket
serebii.net
AMANSA retweeted
We'd like to share a letter from the Pokémon TCG Pocket Operations Team detailing our development plans and planned updates coming to #PokemonTCGPocket with the new series.
Thank you for being a part of the community and for your continued support of the game.
AMANSA retweeted
We're building self-improving agents to automate tedious, repetitive operational work @GrepdotAI. At IG, a UK online brokerage, Grep agents review compliance alerts, helping over 80% of traders onboard without manual intervention. IG is now a FTSE 100 company.
Operational work often means following a specific procedure, gathering information from different sources, checking it against what's needed, and deciding what to do next.
The steps are repetitive, but no job is the same, making the work tedious to do by hand and hard to automate with workflows alone. Meanwhile, using frontier agents to reason through every task is often too expensive to scale.
Grep.Al gives you an agent workforce that:
-> Takes minutes to create and are domain experts with the right skills and tools from day one.
-> Learn from every run, moving repeatable steps into code and workflows and saving frontier intelligence for exceptions and unfamiliar cases.
-> Get smarter and cheaper as they scale using our AgentRun harness.
-> Runs on our managed agent platform with secure sandboxes, audit logs, evals, cost controls, team sharing, and access controls included.
Grep AI agents are available on demand and can run on schedules or in batch. Access them via the console, MCP, API, or SDKs that integrate into your existing workflows.
Our customers, including IG, Airwallex, Worldpay, FV Bank, and Citizens Bank, have saved more than 250,000 hours of operational work with Grep Al agents across onboarding, doc verification, compliance, underwriting, operations, HR, GT ops, market research, and business intelligence.
If operational bottlenecks are slowing your business down, create an agent workforce with Grep to automate them in minutes.
P.S. We're in the @ycombinator Fall 2026 batch!
AMANSA retweeted
The latest game information has been announced at #PokemonXP 📣
Even more Basic Pokémon ex are set to appear, and they're being joined by the introduction of powerful Dual-type Pokémon ⁉️
Get ready, as a new series of #PokemonTCGPocket is coming October 2026!
AMANSA retweeted
Be on the lookout 🚨
We're hearing increasing reports of an unknown group causing disorder and disturbance 👤
AMANSA retweeted
🚨5x OAK GIVEAWAY🚨
🍀5 lucky winners will obtain a Full Art Professors Research Card🍀
-How to enter-
💚Like and Repost
👤Follow @HilightOfficial
💬Comment what Mega Pokemon you want to see next in the game
📣Winner will be announced on August 17th!
#PokemonTCGPocket
AMANSA retweeted
🌟 Pokémon TCG Pocket Info🌟
✅ The next teaser will be released on August 19 (B4a)
✅ The next trailer, for B4a, will be released on August 20
✅ The set B4a will be released on August 27
✅ TCG Pocket Panel Stream at Pokémon World Championships will start on August 29
#PokemonTCGPocket
AMANSA retweeted
🎉¡SORTEO TCG POCKET!🎉
Premio: Prof. Oak ⭐️⭐️ (ENG)
Sponsor: @jeg_bovonto ♥
Para participar:
1️⃣ Seguir a @TheMakyokyo
2️⃣ Repostear este tweet
3⃣ Aceptar Disclaimers
Ganador: Se anunciará el Viernes 14/8
¡Suerte entrenadores! 🤩
#PokemonTCGPocket #TCGPocket
AMANSA retweeted
Here's a preview of the upcoming events planned for the #RulerOfTheSkies expansion!
Who else is planning to try out Mega Houndoom ex 👀
AMANSA retweeted
Some good best practices here on AI token cost optimization. None of these happens though without a deep understanding of the underlying work being done in a non-abstract way.
The ultimate implication is that a layer between the work itself and the underlying intelligence needs to deeply understand your workflows, context, and business process. Now, each individual company doing this on their own is unlikely to be effective at scale, so as a consequence, this is effectively the playbook for any applied AI company right now.
By evaling the models for the applied use cases, deeply understanding the domain, having tuned UX and features for the use case, and having the ability to support adoption and change (via FDEs), allow this layer to add a ton of value. And as a result, enterprises get higher ROI because you actually can get *more* intelligence per dollar by having optimal architecture and workflows.
There will be many horizontal and vertical versions of this approach. Huge opportunity right now.
How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching.
Better Defaults (not Usage Caps) – Engineers can choose any model they want, but defaults matter. We’re experimenting with defaulting to open weight models like GLM 5.2 and Kimi 2.7 through our LLM gateway, while still encouraging engineers to choose the right model for the task. 91% of our employees were never hitting their usage caps, so instead of lowering caps and driving up alerts, we're moving to cheaper defaults. Note that code reviews use a diversity of models, so they can check each other's work.
Better Routing – In our custom harnesses, we preprocess prompts and route to the best model for the job, considering cache hits and model pricing. For instance, you may want a frontier model for planning, but not for execution where they can be overkill. Ultimately, humans shouldn't be choosing models - AI can automate this task.
Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. For example, our cache hit rate went from 5% → 60% in LibreChat once properly implemented.
Keep Context Lean – Start fresh sessions when switching tasks. Scope file context narrowly. Disconnect unused tools. Don't just compact. The goal isn't fewer tokens used, it's fewer tokens wasted.
Better Visibility – Our engineers can use as many tokens as they want, from whatever model they want, but we’ve made usage visible – and the more you spend on AI, the more impact we expect.
The goal isn't to suppress usage. It's to build the infrastructure that makes exponential growth sustainable.
Putting this into practice has cut our AI spend nearly in half, while our token usage continues to grow.
AMANSA retweeted
GLM-5.2 is the open-source Claude moment.
The demand we’re seeing at Databricks is astonishing. The world is going to see massive adoption of oss LLMs.
Also, more companies will shift toward post-training their own models on top of oss models and owning the weights.
AMANSA retweeted
Someone should productize this. A coding harness that automatically routes to the lowest cost smart enough model for each request.
How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching.
Better Defaults (not Usage Caps) – Engineers can choose any model they want, but defaults matter. We’re experimenting with defaulting to open weight models like GLM 5.2 and Kimi 2.7 through our LLM gateway, while still encouraging engineers to choose the right model for the task. 91% of our employees were never hitting their usage caps, so instead of lowering caps and driving up alerts, we're moving to cheaper defaults. Note that code reviews use a diversity of models, so they can check each other's work.
Better Routing – In our custom harnesses, we preprocess prompts and route to the best model for the job, considering cache hits and model pricing. For instance, you may want a frontier model for planning, but not for execution where they can be overkill. Ultimately, humans shouldn't be choosing models - AI can automate this task.
Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. For example, our cache hit rate went from 5% → 60% in LibreChat once properly implemented.
Keep Context Lean – Start fresh sessions when switching tasks. Scope file context narrowly. Disconnect unused tools. Don't just compact. The goal isn't fewer tokens used, it's fewer tokens wasted.
Better Visibility – Our engineers can use as many tokens as they want, from whatever model they want, but we’ve made usage visible – and the more you spend on AI, the more impact we expect.
The goal isn't to suppress usage. It's to build the infrastructure that makes exponential growth sustainable.
Putting this into practice has cut our AI spend nearly in half, while our token usage continues to grow.
AMANSA retweeted
This is very interesting. Coinbase seems to have lowered their token spend ($$) to about half, by
1) routing to cheap inference like GLM 5.2 and Kimi 2.7 that are still pretty performant
2) Smart routing + caching
They still use the same tokens as before. Start of a trend?
How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching.
Better Defaults (not Usage Caps) – Engineers can choose any model they want, but defaults matter. We’re experimenting with defaulting to open weight models like GLM 5.2 and Kimi 2.7 through our LLM gateway, while still encouraging engineers to choose the right model for the task. 91% of our employees were never hitting their usage caps, so instead of lowering caps and driving up alerts, we're moving to cheaper defaults. Note that code reviews use a diversity of models, so they can check each other's work.
Better Routing – In our custom harnesses, we preprocess prompts and route to the best model for the job, considering cache hits and model pricing. For instance, you may want a frontier model for planning, but not for execution where they can be overkill. Ultimately, humans shouldn't be choosing models - AI can automate this task.
Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. For example, our cache hit rate went from 5% → 60% in LibreChat once properly implemented.
Keep Context Lean – Start fresh sessions when switching tasks. Scope file context narrowly. Disconnect unused tools. Don't just compact. The goal isn't fewer tokens used, it's fewer tokens wasted.
Better Visibility – Our engineers can use as many tokens as they want, from whatever model they want, but we’ve made usage visible – and the more you spend on AI, the more impact we expect.
The goal isn't to suppress usage. It's to build the infrastructure that makes exponential growth sustainable.
Putting this into practice has cut our AI spend nearly in half, while our token usage continues to grow.