Ricardo Jaimes (Tripl3)

AI Engineer | Building sat-mcp, a production MCP server (46 tools, 6.6k tests) powering DISAI-Conta: Agentic fiscal compliance for Mexican accountants

[Ricardo Jaimes (Tripl3) @TripleeeTres]

https://t.co/hQeZd8qt4T

[Codez @0xCodez]

https://t.co/OKJyooXqTc

[Kun Chen @kunchenguid]

now that the dust is settling around the last wave of model releases, and i've had enough time to use all these models in practice, let me share a more complete set of thoughts

1. grok 4.5 is probably the single most significant event during the last couple of weeks

i've been talking with many heavy users across model families, and it's pretty much a consensus that grok 4.5 is the most "pleasant" frontier model to work with day to day. it's incredible how precisely the team behind it found this perfect sweet spot and created a model that's so fast, efficient and capable

it proved spacexai is now a 3rd real player in addition to anthropic and openai. they have real time data from the biggest public townsquare of humans, they have acquired a popular agent harness, and now they have proven they can build great models. and if you look closely, they are designing their own chips, they have their own data centers, they can send GPUs into the space and create tokens out of sunshine

holy shit

2. speaking of data, human usage over a harness proved to be extremely important for training good models. grok 4.5 was the first model that incorporated cursor's data and it made a massive difference compared to previous generations of grok

this explained why amazon mandates employee usage of kiro, why meta installed mass surveillance over employee devices, why anthropic bans 3rd party harnesses, and why google is still struggling with gemini - because they don't have a popular harness with mass adoption to collect the data

this is part of why i don't think the subsidized LLM subscriptions will end any time soon, because a wide consumer adoption is the best source of data collection. we're paying the subsidized tokens by teaching their models how to get work done

3. opus 5 flopped. almost no one likes it. the only people who like it seem to be using it to one-shot 3d games that look impressive but no one will ever buy

anything that AI can one-shot is just the definition of garbage, because if you can one-shot this thing with a quick prompt, you should know that it means billions of other people can also do it - you will not create anything of value this way

and this is just a symptom of a more fundamental problem that model training is heading down a slippery slope where machine verifiable outcome is dominating over human feedback

the latest training process rewards the agent for running for a long time and finishing a complex project, yet no longer seems to care about how the agent talks to its human

jargons, walls of text, "an honest mistake" - opus 5 showed us that we need AI that's more human friendly. let's not build a world where we end up working with robotic a**holes all day

4. fable 5 remains undefeated as the upperbound

i talked about this in my previous post about wisdom vs diligence. the benchmarks blend both together so it's not easy to see, but fable 5 is the GOAT on the "wisdom" dimension despite it not winning on every benchmark. if you used it meaningfully, you know what i'm talking about

that said, it seems anthropic is extremely paranoid about other players, including open models, reaching the same level of intelligence, which is an indication that the moat is not strong. kimi k3 is just a preview of what it looks like

at the same time, fable is the first time token cost is becoming a very real problem. it's the only model so far that i can't afford to keep using all day. i suspect this will remain true for a while, that we have to pick and choose what tasks to give to fable-tier models, not using them as a daily driver

5. openai is in an interesting position

gpt models have been great at efficiency, but now grok is also very competitive. gpt also haven't quite reached the same wisdom upperbound where fable is yet - although gpt 6 may change that

i think there are two angles for openai to pursue:

- continue to bet on efficiency, and go after enterprise adoption while claude is too expensive and grok has a brand tax to pay there. this is a very viable strategy

- or.. compete head on with fable on wisdom and win against them on the "human friendly" aspect. although traditionally this hasn't been the strength of openai models either, so this feels like a low-ROI option

alright, that's a bit of a long post but the landscape is just becoming increasingly complex. hope these thoughts are helpful in terms of providing a reference for how to rationalize everything happening

[Uncle Bob Martin @unclebobmartin]

People keep on telling me that my message about AI is undercutting my own books. Those people do not understand how agents work and who actually controls them. You can't tell an agent to be clean. You have to measure the cleanliness that they produce and have them correct failures of cleanliness.

Without such constraints agents are more than happy to build big balls of mud that they can't maintain.

[Ricardo Jaimes (Tripl3) @TripleeeTres]

No te pierdas mi último artículo: El riesgo fiscal no vive a un salto: la matemática detrás de efos-risk-graph https://t.co/1Vn3X8LyFm via @LinkedIn

[Steve Huynh @ALEngineered]

Prediction: There will be more demand for software developers 2026-2030 than there was from 2020-2025.

[Uncle Bob Martin @unclebobmartin]

Refactoring with agents is _so much fun_! Extract this! Move that! Integrate those! All the power, none of the headache.

[Ricardo Jaimes (Tripl3) @TripleeeTres]

Determinism isn't a property of the model, it's a property of the system you build around it. Spent the last year on AI-native fiscal compliance for Mexico's SAT and that was the whole game: let the LLM own intent, extraction and routing, and put the math, the validations and anything irreversible behind an MCP tool boundary where it's deterministic and gated. Probabilistic where a wrong guess is cheap, deterministic where it isn't.

[Pavel Durov @durov]

🌍 This summer will see the largest rollout of a non-custodial crypto wallet in human history.

⚡️Instant zero-fee crypto transactions for over a billion users are about to become reality.

We're bringing a native non-custodial Gram wallet to every Telegram app! 💎

[Param @ParamSiddh]

1. Algebra is good for problem-solving.

2. Geometry is good for visual thinking.

3. Calculus is good for understanding change.

4. Statistics is good for decision-making.

5. Number theory is good for logical discipline.

6. Linear algebra is good for modern science and engineering.

7. Discrete math is good for computer science.

8. Differential equations are good for modeling the real world.

9. Optimization is good for smart planning.

10. Graph theory is good for network thinking.

11. Set theory is good for structured reasoning.

12. Practice is good for mathematical fluency.

13. Curiosity is good for lifelong learning in math.

[Mihail Eric @mihail_eric]

The new syllabus for my Stanford course 𝗧𝗵𝗲 𝗠𝗼𝗱𝗲𝗿𝗻 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 is coming along nicely. The AI coding world has changed a lot since last September. The new class will be bigger, more difficult, more fun.

More exciting things coming soon!

[Coin Bureau @coinbureau]

JUST IN: Base founder Jesse Pollak steps back from app leadership after admitting his social bet "was wrong"

Pollak said Base's bets on Farcaster, Zora, miniapps, and creator coins "disintegrated completely" in Q1 2026 and called the experience "a punch in the face."

Cobie will now lead the Base app after Coinbase acquired his launchpad Echo for $375 MILLION.

Pollak says "I am now focused on bringing a billion people onchain just by making global finance actually work."

[Guillermo Rauch @rauchg]

Make the model a cog in a machine you own.

◾ AI SDK → open model API
◾ https://t.co/O7y9dmUqk5 → open Agent API
◾ AI Gateway → open ZDR inference

Startups and enterprises must own their data, evals, model choices, software layer. Don't outsource your brain.

[Sam Altman @sama]

homeboy you're the one sellling public market investors on short-term space datacenters

[ClaudeDevs @ClaudeDevs]

6 months of Claude Max 20x, on us.

We're expanding Claude for Open Source to more of the community.

If you're a maintainer, a core contributor, someone landing PRs across the ecosystem, or someone keeping a critical package alive, apply today!

[Ricardo Jaimes (Tripl3) @TripleeeTres]

👀

[Seb ⚛️ ThisWeekInReact.com @sebastienlorber]

TypeScript 7.0 is officially out, and it's much faster!

Up to 16x faster with increased type-checking parallelization

[diva @divaagurlxw]

As an AI Engineer. Please learn

>Harness engineering, not just prompt engineering

>Context engineering, not just long prompts

>Prompt caching vs. semantic caching tradeoffs

>KV cache management, eviction, reuse, and memory pressure at scale

>Prefill vs. decode latency and why they optimize differently

>Continuous batching, paged attention, and throughput optimization

>Speculative decoding vs. quantization vs. distillation tradeoffs

>INT8, INT4, FP8, AWQ, GPTQ, and when quantization hurts quality

>Structured output failures, schema validation, repair loops, and fallback chains

>Function calling reliability, tool contracts, argument validation, and idempotency

>Agent guardrails, loop budgets, tool budgets, and termination conditions

>Model routing, graceful fallback logic, and degraded-mode UX

>RAG architecture: chunking, embeddings, hybrid search, reranking, and freshness

>Retrieval evals: recall, precision, grounding, attribution, and citation quality

>Evals: golden sets, regression tests, adversarial tests, LLM-as-judge, and human evals

>LLM observability as a first-class discipline: traces, spans, tokens, latency, errors, and drift

>Cost attribution per feature, workflow, tenant, and user journey not just per model

>Safety engineering: prompt injection defense, data leakage prevention, and permission boundaries

>Multi-tenant isolation, cache safety, and cross-user context contamination prevention

>Fine-tuning vs. in-context learning vs. RAG vs. distillation and when each is the wrong tool

>Latency, quality, cost, and reliability tradeoffs across the full inference stack

>Production failure modes: hallucinated tool calls, malformed JSON, stale retrieval, runaway agents, and silent eval regressions

[CyrilXBT @cyrilXBT]

THE JOB MARKET IS ABOUT TO GET WEIRD.

And most people are not prepared for what is coming.

Companies in 2026 are not looking for data scientists.
They are not looking for ML engineers.
They are not looking for people who can build models from scratch.

THEY ARE LOOKING FOR AI NERDS.

The person who walks into a meeting, sees a 4 hour manual process, and kills it in 10 minutes with Claude Code and LLMs.
The person who refuses to do anything manually twice.
The person who looks at every repetitive task and asks one question:

Why is a human still doing this.

That mindset is worth more right now than a machine learning PhD.
More than five years of Python experience.
More than any certification from any university.

THE NEW VALUABLE SKILL IS NOT TECHNICAL.

It is a refusal to accept inefficiency.

The people who develop that refusal this year will be completely unemployable in the old way and completely irreplaceable in the new one.

Which side of that line are you on.

[GREG ISENBERG @gregisenberg]

The computer is being reinvented in the agentic era:

- The model is the new CPU.
- The harness is the new OS.
- Hallucinations are the new bugs.
- The context window is the new RAM.
- Skills are the new apps.
- Markdown files are the new config.
- Evals are the new QA.
- Context is the new moat.
- Permissions are the new firewall
- Trust is the new bottleneck.
- Prompt is the new programming language
- Agent is the new software.

Anything you dream of, you can build.

This is the greatest time ever to be building with computers.

[jesse.base.eth @jessepollak]

cloudflare is about to update the way content and value is exchanged on the internet