SmartQubit

Red Hat Delivery Specialist - OpenShift, AWS Technical Professional, IBM Advanced Technical Expert, IBM Storage Specialist, VMware Cloud Master, SAN Specialist

[Avi Chawla @_avichawla]

A harnessed LLM agent, clearly explained!

Two agents can run the same model on the same task and finish as expected. But one of them can spend nearly 3x the tokens to complete the task.

The extra usage originates from the code wrapped around them, which decides what reaches the model's context on each call and how many calls there are.

For instance, consider a tool that returned 50k tokens of JSON at some step. If it stays in the context, the model will continue to read that payload again at every subsequent step.

Tool definitions behave the same way.

A server can expose 50 tools, each with a name, a description, and an input and output schema.

By default, all of them will stay in the prompt from the first call, whether the agent uses them or not.

However, an optimally built harness can avoid that unnecessary cognitive load on the model.

More specifically, one core design principle of harness engineering is to push things out of the model at the right time:

- Memory holds the state that weights and context shouldn't carry.
- Skills hold procedural knowledge. These cover the operating procedures and heuristics that specialize a general model.
- Protocols hold the interaction contracts for users, other agents, and tools.

Do note that the context never disappears permanently.

It is always loaded when needed, and the harness decides how much is loaded and when.

For instance, to manage a 50k token payload, a harness can write it to a file and keep a preview and a path in context, hand the work to a subagent whose context is discarded afterwards, or summarize the older messages once the conversation passes a threshold.

If you want to see this in practice, TrueForge is an open-source harness that already implements these practices.

Tool schemas are deferred unless preloading is switched on, large responses go to a sandbox file, and generated code calls tools back through the harness, so the sandbox never holds the credentials.

The two agents I talked about at the top are from DevRev's Enterprise-Bench. TrueForge solved the same number of tasks as Claude Managed Agents on the same model, using a bit over a third of the tokens and around 40% fewer tool calls.

Here's the GitHub repo: https://t.co/ZjePhhfKIh

(don't forget to star it ⭐ )

I also wrote a full breakdown of where agent tokens actually go inside a run, covering context accounting, the strategies above, and the benchmark in detail, and TrueForge worked with me to put this together.

Read it below.

[Nix0n @UnTalNixon_exe]

🚨ATENCIÓN!! Acaban de hacer obsoleto el “necesitas 48 GB de VRAM”.

Un modelo de 20 GB corre a ~100 tok/s en una RTX 5080 de 16 GB.

FreeToken (nuevo motor open-source) trata toda tu máquina (GPU + CPU + RAM) como una sola plataforma de inferencia.

Solo activa los experts necesarios (MoE) + caching dinámico + scheduling inteligente.

8 GB laptop → 35B
RTX 5090 → 284B
Workstation → 753B

Apache 2.0 · Windows/Linux · GUI · API OpenAI compatible

La era del “no cabe → no se puede” acaba de morir.

Repooo👇👇

[S@{I-I{00 @Sachcoo_thearty]

Gamer Consciousness

[Miguel Ángel Durán @midudev]

El creador de Node.js acaba de lanzar Dactyl.

Apps nativas de iPhone y Android desde la web.
Sin Mac. Sin Xcode. Sin Android Studio.

✓ Simulador de SwiftUI en el navegador (WASM)
✓ El mismo código para iOS y Android
✓ Usas TU suscripción de ChatGPT

→ https://t.co/jpkYQzagOE

[Sébastien Dudek 📡 @FlUxIuS]

Proxmark5 support lands in the rfid image with #RFID #Proxmark3 and #Proxmark5 side by side in the same container, plus a hardening pass on the PM3 install and a batch of tool bumps.
🧵

[Maestro @maestro__dev]

AUTOMATE mobile app testing with a flow your team can actually read, trust, and debug.

build these flows in Maestro Studio, or let your coding agent write them through Maestro MCP.

[wast3 @0xWast3]

Anthropic ex-engineer runs an internal graph that costs $6 a month and catches what a $300,000 eval suite misses. No retrieval layer. Seven nodes and one rule about who's allowed to change their mind.

He published the whole schema.

His version starts from the opposite idea. A graph is not an execution order. It's a memory of why.

Seven nodes. Every edge carries the reason it exists:

> INTENT - states what the task is for. Never how
> DECOMPOSE - splits it into steps, each with a stated assumption
> WORKER - executes one step. Sees nothing else
> AUDIT - checks the output against the assumption, not the goal
> DRIFT - compares the current step to INTENT and flags divergence
> LEDGER - stores every decision with the assumption that justified it
> ROOT - holds the graph, and when an assumption breaks, re-runs every step built on it

Six nodes act. One node remembers why they acted. Every step carries the assumption that made it correct, so a false one only reruns what stood on it.

That's the entire design. A pipeline that forgets its reasons has to redo all of it or trust all of it.

He replayed a month of agent runs. 4,100 steps, 380 built on an assumption that was wrong by day three. The old pipeline shipped all 380 and linked none of them.

Everyone else builds graphs where output moves forward and the reasoning evaporates. He built one where the reason travels with the result. The blast radius is the output nobody else produces.

The article below is the full build - node prompts, the assumption format, the invalidation rule that finds every step downstream of a broken one.

Save it. You'll want it open in the other

[Miguel Ángel Durán @midudev]

¿Quieres ejecutar IA en local? Pero no sabes si tu ordenador lo soporta... ¡Usa esto!

✓ Detecta tu GPU desde el navegador
✓ Sin instalaciones ni registros
✓ Para texto, código, imagen y vídeo
✓ Apple, NVIDIA, AMD, y mucho más

→ https://t.co/bvZVTPoAud

[Crémieux @cremieuxrecueil]

This is a super cool website.

You can scroll around and look at any country's population pyramid, fertility rate, and mortality rate by year.

Check this out:

[J.B. @VibeMarketer_]

call me crazy but the first AI agent most companies should build is an autonomous analyst.

you can build one using Kimi K3.

it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on.

don't bookmark this if it crosses your timeline.

paste the full article into Kimi and tell it to build the first version for your market.

[Nix0n @UnTalNixon_exe]

CAPTURAR MOVIMIENTO DE CUERPO COMPLETO CON SOLO 4 SENSORES

Esto es GRIP.

Solo 2 smartwatches + 2 plantillas de presión.
Y reconstruye el movimiento completo del cuerpo de forma físicamente realista.

No flota.
No se desliza.
No atraviesa el suelo.

Usa un gemelo digital físico (humanoide controlado por torques) para que cada paso, salto o equilibrio respete la gravedad y las fuerzas de contacto.

Antes necesitabas trajes caros de motion capture o 20+ sensores.
Ahora basta con lo que ya llevas en las muñecas y en los pies.

Paper aceptado en CVPR 2026.
Código y dataset disponibles.

Este es el futuro de la captura de movimiento wearable.

Repoo 👇

[Snow Brave @Sn0wbrave]

Fleetbase 🚚

منصة مفتوحة المصدر لإدارة العمليات اللوجستية وسلاسل الإمداد، تساعد الشركات على إدارة الطلبات، التوصيل، الأسطول وتتبع الشحنات من مكان واحد.

[Red Hat Services @redhatservices]

Facing rising #virtualization costs? Our @RedHat Virtualization Migration Assessment helps you identify optimization opportunities and creates a strategic plan to modernize your infrastructure without the disruptive overhaul. Learn more: https://t.co/vKVJfUKXgh

[Artificial Analysis @ArtificialAnlys]

Kimi K3 scores 57 on the Artificial Analysis Intelligence Index. Its intelligence is comparable to Opus 4.8 and GPT-5.5 but remains behind Fable 5 and GPT-5.6 Sol. Moonshot AI has expressed plans to release the 2.8T parameter model's weights, which would make it the leading open weights model

Key results:

➤ Strong agentic task performance: @Kimi_Moonshot's Kimi K3 reaches an Elo rating of 1668 on GDPval v2. This is a marked improvement over K2.6’s 1190, surpassing GLM-5.2 (1514), GPT-5.5 (1494), and Claude Opus 4.8 (1600). However, it still lags behind Claude Fable 5 (1760). Kimi K3 also scores an impressive 53% and takes the #1 position on AutomationBench-AA, our implementation of Zapier’s Agentic SaaS workflow evaluation.

➤ Second-highest performance on AA-Briefcase (agentic knowledge work): On our private long-horizon knowledge work evaluation, Kimi K3 reaches an overall Elo of 1547, +732 points from Kimi K2.6 and behind only Claude Fable 5. It is well-rounded: its rubric scoring and analytical quality almost reach Claude Fable 5’s scores, while GPT-5.6 Sol continues to outperform other leading models on presentation quality.

➤ Set to lead open weights models once weights are released: Moonshot AI has not yet released the weights but expressed plans to do so. Once available, Kimi K3 would clearly lead other open weights models including GLM-5.2 (51) and DeepSeek v4 Pro (44). However, at 2.8T parameters, it is significantly larger than its open weights peers (eg. GLM-5.2 at 753B params and DeepSeek V4 Pro at 1.6T), as well as the Kimi K2 to K2.6 models (1T params).

➤ Cost per task ($0.94) is similar to GPT-5.6 Sol ($1.04), ~1/2 the price of Opus 4.8 ($1.80) and higher than open weights peers: Moonshot AI’s pricing for K3 is significantly higher than their K2 pricing (K3’s output token price is $15/1M tokens while K2.6 was $4). This positions the model as cheaper on a cost per task basis than Opus 4.8, similar to GPT-5.6 Sol ($1.04) and more expensive than open weights peers, GLM-5.2 ($0.32) and DeepSeek V4 Pro ($0.04)

➤ Improved token efficiency alongside higher intelligence: Kimi K3’s token usage on the Artificial Analysis Intelligence Index decreased significantly, using 21% fewer output tokens than K2.6. The new model used approximately 132M output tokens to complete all nine evaluations, compared to approximately 166M for K2.6, while achieving higher scores.

➤ Native multimodal capabilities: Kimi K3, like K2.6, is released with native image and text multimodal input. If weights are released, this will position Kimi K3 as one of the leading open weights models with multimodal input capabilities

Other model details:

Context window: 1M

Size: 2.8T total parameters

Pricing: The first-party API is priced at $3.00/$15.00 per 1M input/output tokens, with cached input discounted 90% to $0.30 per 1M tokens.

Modality: Native multimodal input supports text and images, and the model remains text-only for output.

Accessibility: Accessible at launch through Moonshot’s first party API. Model weights are not yet released but Moonshot AI has expressed plans to do so.

[Arena.ai @arena]

Exciting update: Kimi K3 has landed at #4 on the Agent Arena leaderboard, matching Claude Opus 4.8 and GPT-5.6 Sol. If Kimi K3's weights are released on schedule by July 27, it will become the #1 open-weight model.

This release marks a major leap in agentic performance over Kimi K2.7 Code (#23 to #4). Based on 8K+ live agentic sessions, Kimi K3 leads on confirmed task success rate (#1). It also posts a strong +20.6% on praise vs. complaint (#3). It currently lags the field in steerability (#14) and bash recovery (#17).

Agent Arena measures models on millions of real-world, long-horizon agentic tasks. Models get web search, filesystem, and terminal tools to complete complex workflows: writing code, creating slide decks, researching the web, building apps, and analyzing documents.

We use causal tracing methodology to measure a model's net improvement, which indicates how much it improves outcomes relative to the average model.

Here's a primer on the 5 signals:

User-satisfaction proxies
- Confirmed Success: an explicit "yes that worked" feedback from the user
- Praise vs. Complaint: implicit sentiment in users reactions
- Steerability: can the model course-correct when you push back?

Tool-use proxies
- Bash Recovery: how it recovers from CLI errors (primary signal for tool use)
- Tool Hallucination: does it call tools that don't exist

Below we break down how Kimi K3 scored across the 5 signals, drawn from tasks submitted by a global community of users.

Congrats @Kimi_Moonshot on another big milestone!

[Arena.ai @arena]

Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5.

This is a 17-place jump from Kimi-k2.6 (#18 -> #1).

In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Simulations, and Content Creation Tools, landing #2 only in Gaming behind Fable 5.

The full model weights will be released by July 27.

Congrats to the @Kimi_Moonshot team on this major milestone!

[elhacker.NET @elhackernet]

PentesterFlow: IA para automatizar flujos de pentesting y bug hunting

PentesterFlow es una nueva herramienta de línea de comando basada en IA agentica de código abierto, diseñada específicamente para cazadores de recompensas (bug bounty) y pentesters
https://t.co/qk3Cdz02Fv

[beamnxw ./ @beamnxw]

https://t.co/Qd15VI1bFb