Linguista computacional | e/acc 🤖 | Positivista | Judío...(ish) | Liberal Clasico | Professional overthinker | Amateur tissue culture grower | 🇮🇱 | 🇨🇴
Earth
Joined April 2009
- Tweets22.4K
- Following2.2K
- Followers808
- Likes21.7K
Pinned Tweet
Si Odiseo le hubiera explicado a Euríloco qué escondía realmente el canto de las sirenas, habría descrito el retrato exacto de lo que fuimos: "Todo lo que soñabas ser y todo lo que desearías no haber deseado jamás", La certeza de que lo que más ansiabas era inalcanzable, y que eso inalcanzable era, irónicamente, lo que ya tenías entre las manos antes de perderlo.
Creo que, por un instante, logré escuchar el canto de una sirena.
Y eras tú.
Juan Jose Alban retweeted
Asimov 1 is an open-source humanoid robot you can build, train, and customize.
- 1.2 m tall, 35 kg
- 25 powered joints
- Open hardware with off-the-shelf parts
- Open-source SDK and simulation models
Available as a DIY kit.
Order yours at menlo.ai/order
Juan Jose Alban retweeted
Información de TransMilenio en tiempo real, vía API y MCP
TransMilenio publica la posición de cada bus cada 20 segundos, y desde hoy está en Croma. Hoy a las 7 de la mañana había 7.853 buses en vía en Bogotá
De "te quiero, cómo quiero a mi libro favorito"
A "te quiero, porque me presentaste mi libro favorito".
Lo que viene nl congreso... una transposición clásica (1.e4 e5 2.Cf3 Cf6). DlaEspriella (bln) abre con su Ajuste Fiscal. El Pacto Histórico (ngr) espejea la ofensiva: aprueba algunos artículos de recaudo, pero bloquea las cláusulas de contracción del Estado y privatizaciones.
El 27 de octubre de 2012 cambio mi vida de muchas formas bonitas, conocí a mucha gente bonita, conocí amores, compañeros de trabajo y jefes. Viajé :)
Fue la primera vez en mi vida que viaje solo y por mis propios medios.
Fue la primera vez que pisé Tunja...
Juan Jose Alban retweeted
Prometer becas en el SENA es como prometer que en Bogotá se destinará un fin de semana anual para que bandas de rock den conciertos sin cobrar un peso para ingresar al público.
Juan Jose Alban retweeted
Ser pro Palestina, no debería ser una contradicción al sionismo, si el fin fuera buscar paz.
Sionista es aquel que reconoce el derecho de la existencia de Israel.
Podrían coexistir los dos, en paz y beneficiándose mutuamente.
1/3
Juan Jose Alban retweeted
Los musulmanes tienen un problema con la música, con los perros, con los cerdos, con las mujeres, con las personas homosexuales, con los cristianos, con la libertad de expresión y con la democracia.
Pero si yo tengo un problema con los islamistas, entonces el intolerante soy yo
Juan Jose Alban retweeted
This might be the most useful paper on AI agents this year.
A team at Wavestone AI Lab took apart Claude Code, Codex and 9 more and found the 7-part blueprint every good agent is built on.
Their definition: an agent is a model plus a harness. All 11 agents build the harness from the same 7 parts. Only the size changes.
> Loop: Mini-SWE-Agent is a plain while loop. OpenHands logs every event so a run can be replayed
> LLM layer: one prompt template on one side, 29 provider profiles on the other
> Tools: some agents only have bash, the biggest has 43 typed tools loaded on demand
> Memory: from keep-the-whole-history to notes the agent maintains across sessions
> Safety: from a simple step limit to policy rules plus a reviewer model plus an OS sandbox
> Orchestration: Aider skips sub-agents on purpose, others fork them with their own context
> Extensions: hooks, skills and MCP. SKILL.md is in 9 of 11, MCP in 8
The paper ends with a 90-line harness covering all 7 parts, a solid starting point for your own.
Key pages:
> p.4: the 7-part map
> p.12: the 3 loop types, with Claude Code and Codex as examples
> p.53: why none of them use frameworks or embeddings
> p.67: 18 design recommendations
> p.71: the 90-line harness you can copy
Juan Jose Alban retweeted
Indeed. And the « neo-vitalists » who affirm that consciousness requires biological hardware and will always remain beyond AI’s reach are equally misguided, in my opinion.
“Do not bet against the airplane. The skeptics who say AI can't conjecture, can't theorize, and can't explain are describing last spring's models. Within months, that description will no longer hold. The evidence is clear, and those with eyes can see it. Anyone who stakes their identity on "AI can't do task X" is building on sand.” Indeed.
Juan Jose Alban retweeted
Huge release from EverMind AI.
Raven is an open-source multi-agent system that builds a separate harness for each model and domain, evolves those harnesses from their failures, and coordinates them through a host agent.
The host agent splits a goal into a task graph and sends each part to a model-harness pair for research, code, design, or on-call work.
Harness components are diagnosed, mutated, and recombined, and a candidate replaces the current harness only after passing a statistical check.
With DeepSeek-V4-Flash, the research harness scores 69.3% on BrowseComp and 60.0% on Humanity's Last Exam, against at most 62.4% and 43.3% for two other harnesses on the same model.
Its curated skill library raises SkillsBench Pass@1 from 9.2% with no skills to 22.6%.
Paper: arxiv.org/abs/2609.33439
Chat with Paper: academy.dair.ai/papers/raven…
Juan Jose Alban retweeted
8.
Los árabes demoraron décadas para apropiarse del gentilicio, luego q el pueblo Judío (los conocidos originalmente como Palestinos) adoptara el gentilicio "Israelí".
Reitero y aclaro, cuando yo era niño, los Judios eramos "Palestinos" y los Árabes, "Árabes".
FIN.
COMPARTIR.
Juan Jose Alban retweeted
El musulmán se mandó un moco, te lo tomo. Pero estaba solo. Los israelíes eran más de 100. ¿No te parece una respuesta desproporcionada?
Juan Jose Alban retweeted
Qué forma tan cruel y cobarde de terminar una relación: no tener el valor de decir que ya no quieres continuar y, en su lugar, empezar a alejarte, mostrar indiferencia y enfriar el vínculo hasta que la otra persona se canse de luchar por algo que ya no estás dispuesto a cuidar.
Juan Jose Alban retweeted
Jev Founder, Diogo Almeida, just released a 12-page PDF on how to use Jev with LLMs
It is more useful than most paid AI courses:
this is a 10-step blueprint on how to build a faster, cheaper and more controllable AI system around Claude, Codex, Grok or any other LLM:
step 1 → split the responsibilities: the LLM generates, Jev makes bounded semantic decisions and deterministic code keeps authority
step 2 → build the state: give Jev the current request, relevant evidence, policy and proposed action instead of sending the entire conversation
step 3 → choose the right primitive: Choice selects a route, Score evaluates an ordered rubric and Noul returns the probability that a statement is true
step 4 → replace giant evaluation prompts with atomic questions: intent, urgency, evidence, risk and scope become separate typed decisions
step 5 → put Jev before the LLM: select the context, tools, provider and workflow before paying for an expensive generative call
step 6 → give the LLM a bounded job: once Jev selects the route, the model receives only the instructions, files and tools required for that branch
step 7 → put Jev after the LLM: check whether the result answers the request, uses sufficient evidence and stays inside the permitted scope
step 8 → route by confidence: high-confidence low-risk cases proceed automatically, uncertain cases request more context and consequential actions go to review
step 9 → batch independent decisions: ask multiple Choice, Score and Noul questions over one shared state instead of creating another LLM call for every judgment
step 10 → record the complete decision receipt: state version, question, probabilities, selected route, model, latency, outcome and human override
most AI courses teach you how to write a bigger prompt
this 12-page guide teaches you how to build the control system around every prompt
the result: smaller contexts, fewer unnecessary LLM calls, safer tool execution and decisions you can actually inspect, test and improve
Send this PDF and the original Jev article to Claude Code or Codex and start rebuilding one expensive LLM decision at a time ↓
Juan Jose Alban retweeted
Send this Jev prompt to any LLM or AI agent
It sets up Jev → analyzes you → finds where you waste time and money → upgrades your AI setup beyond 95% of people...
Copy this now. Thank me later:
