
Founder of AQP Intelligence · I build AI agents that do real work · 🏆 1st place @NousResearch Hermes Agent Plugin Hackathon with Foreman · ES/EN
Arequipa, Peru
Joined January 2010
- Tweets110
- Following437
- Followers166
- Likes389
Pinned Tweet
Agents scored ~1,000 entries, humans picked the winners. That's exactly Foreman's idea: an agent shouldn't grade its own work.
1st place 🏆 Thanks @NousResearch!
github.com/PedValme/foreman
6
11
1,629
Replying to @PedValme @NousResearch
Los agentes puntuaron ~1.000 participaciones y los humanos eligieron. Esa es justo la idea de Foreman: un agente no debe calificar su propio trabajo.
1er puesto 🏆 ¡Gracias @NousResearch!
github.com/PedValme/foreman
1
1
101
Foreman, a @NousResearch Hermes Agent plugin: a green check your agent did not rig.
A gate blocks skipped or deleted tests, a changed check and secrets. A second model reviews what rules can't see. You approve from Telegram, then it merges.
github.com/PedValme/foreman #HermesAgent
Big news: Claude Fable 5.2 (Max) by @AnthropicAI takes #1 in Agent Arena with an unprecedented lead: +30.4% net improvement, about 1.6x the #2 model Opus-5.5, across 4.7k real-world agentic sessions from our global community. It's also #1 in Code, Chat and Work.
A major leap over Claude Fable 5.1 (Max)
- Rank: #5 → #1, Net improvement: +14.8% → +30.4%
- Median cost per task: $7.7 → $7.3 (6% lower). The API pricing $10/$50 → $8/$40 per million input/output tokens (20% lower)
vs. The Frontiers
- #1 Claude Fable 5.1 (Max): +30.4% | $7.3/task
- #2 Claude Opus 5.5 (Max):+19.5%) | $5.5/task
- #3 Gemini 4 Carbon (High):+17.0%) | $1.5/task
- #6 GPT-6-Astra (Max): +14.5% | $6.0/task
Breaking down performance across signals:
Fable 5.2 improves over 5.1 across all four reported signals, with particularly large gains in user satisfaction and steerability.
- #1 Praise vs. Complaint , +73%, biggest jump vs +41% the next model.
- #1 Steerability: +33%
- #1 Confirmed Success: +22%
- #3 Bash Reliability: +14%
#1 across all major categories
- #1 Code: +34%
- #1 Work: +31%
- #1 Chat: +27%
- Versus Fable 5.1: Code #6 → #1 (+19.8 %), Work #4 → #1 (+15.8 %), Chat #6 → #1 (+12.0%).
Huge congrats to the @AnthropicAI team on this incredible release!
Pedro Valencia retweeted
Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less "two groups of people speaking past each other" and more a sharp funnel.
- Napkin math somewhere around 6B people (~75% of the population) have barely come in contact with LLMs at all.
- Around 1-2B (~20%) are casual and infrequent users of free-tier ChatGPT-like products. This group sees derpy chatbots and treats them a bit like a better Google search, a writing aid, or etc. Maybe an agent tries to book you a flight. I have non-tech friends who (reasonably, imo) say they have not much use for it at all. Even many professionals outside of math&code are in this tier. For example, execs and many other functions spend a lot of their time talking to other people, so while they understand what is happening intellectually, it is still second-hand and a bit abstract.
- Now we get to professional use of frontier-grade LLMs in math&code. Somewhere around 20M people (0.2%) see first-hand that large, complex projects that used to take them weeks/months can now be completed by agents with a prompt. Building apps, copying apps, translating apps, decompiling apps from binaries... This has all happened very quickly and recently - less than 1 year ago, I was writing code manually by hand, typing memorized computer code commands into a code editor character by character, occasionally pressing Tab to autocomplete a little chunk of code.
- And finally we get to the ~5,000 people (~0.00006%) with access to frontier-grade systems internally. The external world has seen the preview. It looks like swarms of thousands of agents collaborating over weeks on software mega projects: minting zero days, running cyber attacks and defenses at machine speeds, discovering new science, advancing the frontier of mathematics. Things that would have taken top professionals in the industry years of work. Meanwhile, human review and comprehension are starting to fall behind. For example, people are still involved in the "archeology" of the OpenAI-HF incident from many months ago. Mathematicians may be poring over the 722 manuscripts on frontier mathematics for a while.
The funnel is driven by a combination of factors:
1. The impact scales with ambition, problem size, and horizon. A question with a paragraph answer barely stresses the system. You need a reservoir of big, difficult problems that you really care about. This aspect drives the consumer / professional dimension of the funnel.
2. The jaggedness of the system (which I have written about a lot separately). Capability peaks in domains that are digital, verifiable and economically valuable. This is because LLM capability emerges from reinforcement learning on verifiable rewards on a curated environment mixture driven by revenue potential. This aspect primarily drives the area (e.g. math&code) dimension of the funnel.
3. Access. Free-tier, paid-tier, internal.
So this is the weirdness of the moment. The general public has mostly not interacted with these systems. When they have, it looks like a derpy chatbot. The majority of professionals still see only a modest uplift. And a small sliver of professionals are experiencing the vertigo of the curve going vertical. And it is all happening at the same time.
Judging by my tl there is a growing gap in understanding of AI capability.
The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code.
But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along.
So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions.
TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.
Meet Gemini 3.5 Flash — our strongest agentic and coding model yet.
It delivers frontier-level performance at 4x the speed of comparable frontier models — often at less than half the cost.
Generally available, starting today. 🧵
#GoogleIO
Pedro Valencia retweeted
Antes de nada: ¿Quieres estar al día con las últimas tendencias en IA?
Junto a @gptzone_net hemos creado la MEJOR newsletter en español: noticias, prompts, apps, videos y más, ¡todo a diario! 📩
No te pierdas nada del mundo IA.
Suscríbete GRATIS 👇
gptzone.net/suscribete
Pedro Valencia retweeted
¿Qué es el problema de los tres cuerpos?🤔
Seguro que sabes que @NetflixES ha estrenado la serie ‘el problema de los tres cuerpos’, basada en la aclamada serie de novelas de Liu Cixin pero con mucha ciencia detrás.
Pero ¿qué es el problema de los tres cuerpos en física?👇
Pedro Valencia retweeted
Other social media companies too, not just Twitter
Holy sheep shit. The government was actually paying Twitter to censor people.
@elonmusk, maybe there is a way to make Twitter profitable! (Though will cost you your soul.)
Pedro Valencia retweeted
✨🎄Lucky Xmas Gift Event🎄✨
On the occasion of Christmas and New Year, let's cheer this moment with bombcrypto, join the event for a chance to receive a Lucky Christmas gift.
#Bcoin #Bombcrypto #BestWishesForBomb #event #BSC #GameFi #NFTGame
Pedro Valencia retweeted
On DECEMBER 10, 2021, HeroesTD tokens airdrop campaign will be live on CoinMarketCap!
Join us and get your rewards here: coinmarketcap.com/currencies…
#heroestd #nftgame #coinmarketcap
Pedro Valencia retweeted
#MVBIII Expo with October Monthly Stars is here!
🧑🏭7 projects
💰$40,000 in prizes
🎥2 livestreams
Check it out 👇
binance.org/en/blog/join-mvb…
Pedro Valencia retweeted
SORTEAMOS UNA CAJA COMÚN DE @ThetanArena!
Participa muy fácil!
Síguenos @XMGuild
Dale Retweet🔁
Responde a este tweet mencionando a 3 amigos ⬇️
Ganadores el Domingo que viene, suerte!
Pedro Valencia retweeted
Sorteo 20 accesos a la Whitelist de @Titan_Hunters 🔥
Para participar
🔥Seguir a Titan
🔥Conseguir mas de 2500 en la demo (responder con imagen)
🔥RT
🔥Dejar wallet (BEP20) en los comentarios (Es la que tendrá acceso)
Se sortea mañana
Pedro Valencia retweeted
Todo mal 001 - Dos errores youtu.be/jo_usp73Cg0 a través de @YouTube
Pedro Valencia retweeted
Un virtual congresista habla de "pelotudeces democráticas" y quienes apoyan a su partido le piden a su líder que lo bote. Un excandidato amenazó de muerte a dos personas y tú hiciste la "interpretación auténtica" para defenderlo. He ahí la diferencia.
Pedro Valencia retweeted
"la encuesta no midió el debate" es el nuevo "la encuesta no midió el apoyo de Vargas Llosa"
Pedro Valencia retweeted
-Si vas al supermercado, puedes ir a votar.
DeVerdacito
-Si haces picnic con tus amiwis puedes ir a votar.
Franco
-Si vas al gimnasio una vez a la semana puedes ir a votar.
ForReal
-Si te vas de brunch a San Antonio puedes ir a votar.
LaTrue
-Si vas a pinchanguear too.
Serio.





























