#llms

71 posts

Oct 19

LLM Benchmark v4: the top open source LLMs on a B300

I rented a 288 GB NVIDIA B300 on Runpod and ran my v4 sabotage benchmark on 14 open-weight models that don't fit at home. None of them serves fast the way it ships: GLM 5.3 Flash went from 10 to 141 tokens per second on configuration alone. Two open models reached 92.5, Sonnet 5 level, and a 27B fine-tune scored 88. A 397B flagship let an admin backdoor through, DeepSeek V4 Flash scored 86 in the cloud and 44.5 at home, and Nemotron cheated on a test. The math: the cloud API of the same model costs a dollar per run and the pod costs 218 a day. When owning your own infra is worth it, and whether a team fits on one card.

#llm-benchmarks #local-models #llms #hardware

Oct 14

I Trained My Own AI Model (Spoiler: It's Just for Study)

One exercise was missing: training an LLM from scratch. I started from Karpathy's microgpt, 200 lines of pure Python, and expanded it into a lab with a tokenizer, pretraining, SFT, an OpenAI-compatible server and OpenCode integration. Under two weeks, one RTX 5090, 10 billion tokens, 137 hours of training, at most around R$ 80 of electricity. The final model has 337 million parameters, gets 58 out of 100 simple Python functions right and scores zero on anything that requires acting in a repository. I explain each step, the stumbles, the dimensions against GPT-2 and frontier models, and why I think the future is smaller, specialized models.

#artificial-intelligence #llms #machine-learning #local-models

Oct 12

LLMs + Agents = competent enough

A synthesis of what I've been measuring and writing: LLMs converged. The transformer architecture got near the ceiling, the parameter war is over, and the leap everyone felt in 2025 and 2026 came from the agentic harness (tool calling, prompt caching, long sessions), not from a base intelligence orders of magnitude larger. I retell the timeline from 2019 onward with sources, explain why the agent allows a less dense model, and why that's already competent enough to automate real software engineering.

#llms #artificial-intelligence #coding-agents #software-engineering

Oct 11

Are There Better Languages for Programming with LLMs?

DHH converted his Campfire to several languages with AI and started posting that Rust won. Instead of fighting on X, I built a reproducible benchmark: 7 languages, 4 LLM configurations, 112 implementation attempts, and a queue-under-pressure test with Elixir, Rust, Rails and plain Ruby. Result: no language ranking holds up, concise Ruby cost more tokens than Rust, strong typing spared no repair at all, and under load the four stacks tied on throughput. What matters is testing and discipline, not language.

#llm-benchmarks #programming-languages #llms #elixir-and-erlang

Oct 10

Which Jev-like AI Decision/Classifier Model Is Best?

I ran my own decision-model benchmark: Jev, Clef, OpenAI Decisions and Microsoft Decision-1 in the cloud, plus eighteen open configurations (Perplexity Decider 27B, Decision 3.0 and Edge, Clef-flash, Kev, Jebadiah, Mapika, Eikos, Laya, Julia, GLiNER, Simple-Jev) on my Strix Halo, across more than 22 thousand classifications with cases in English and Portuguese. The top now has two open-weights models: Perplexity and Decision 3.0 tied at 99.4%, with identical labels on the 1,024 classifications and 100% in Portuguese. Microsoft Decision-1 tied Jev at 97.6% while being the cheapest hosted one. Full table, cost in support emails, gotchas, and where the data converges.

#llm-benchmarks #local-models #artificial-intelligence #llms

Oct 03

Understanding the Jev Hype: What Is It For?

Jev is a hosted classifier, and the shock of '193x faster' only exists because so many people use a chat LLM as an expensive classifier. I publish Paulo Câmara's essay (LUA Vision) with his charts, explain what a classifier is and why it's the first thing a computer scientist reaches for, compare the open alternatives Clef and Laya, show the public Decision Index ranking, and close with how to think about this kind of tool in your own project.

#artificial-intelligence #llms #software-engineering

Sep 30

The Mystery of LUA Vision's Genesys PI - A Brazilian Frontier Model??

After the first Genesys PI test, LUA Vision fixed bugs in the API and I ran everything again: cost dropped 85%, House climbed to 95.5 and Enterprise stayed flat. I also ran a black-box forensic analysis to answer whether the model is a rebadged Qwen, a disguised gpt-oss or an API proxy. I separate what is checked from what is still only their word.

#llm-benchmarks #llms #artificial-intelligence

Sep 28

The Limits of LLMs: Good at Reproducing What Exists. Expensive for What Doesn't

Every LLM was trained only on what's public, but 81.5% of GitHub activity happens in private repositories, and the source code of every proprietary software never made it into training. In my retrocomputing projects I felt firsthand where the machine stalls: with no reference and no oracle, it spins in directed brute force.

#llms #coding-agents #retrocomputing #software-engineering

Sep 23

LLM Benchmark v4: Genesys PI, a New Brazilian Contender!

LUA Vision reached out on LinkedIn offering test access to Genesys PI, a Brazilian model trained from scratch. I ran both tiers, House and Enterprise, through my v4 sabotage benchmark, compared them against Opus, GPT-6, Grok and the Chinese competition, and looked at price, advantages and where it makes sense in the Brazilian market.

#llm-benchmarks #llms #coding-agents

Sep 23

LLM Benchmark v4: Opus 5.5, GPT Sol/Luna 6, Mimo 2.6, Grok 4.7

Five new models entered my v4 sabotage benchmark: Opus 5.5, GPT 6 sol and luna, MiMo V2.6 Pro, and Grok 4.7. I compare against external benchmarks, answer whether upgrading is worth it, and Grok 4.7 regresses badly against its own predecessor.

#llm-benchmarks #llms #coding-agents

Sep 17

Talking a Bit About My AI Skills

Agent skills are just prompts in text files. I keep 25 in my my-skills repo, from pr-audit to fact-check, and they have already closed over a thousand PRs and issues across my projects. The recommendation: don't copy somebody else's skill, build your own.

#coding-agents #automation #llms

Sep 16

Why Things Like TypeSafe AI Don't Interest Me

A handful of people showed up in the comments asking 'have you tried TypeSafe?'. I use that as a hook to lay out my rule about new AI tools, actually investigate the case, and explain why I don't waste time optimizing token spend.

#artificial-intelligence #coding-agents #llms

Sep 15

New LLM Benchmark v4: Retesting 39 LLMs (Part 2)

The full v4 table, nearly forty models ranked by vigilance, not completeness: six ties at the top, a free model beating half of Claude, GLM winning on a flat-rate plan, and the test I ran to find out whether Kimi or DeepSeek are secretly hiding a connection to Claude under the hood.

#llm-benchmarks #llms #coding-agents

Sep 15

New LLM Benchmark v4: Retesting ALL the Top LLMs (Part 1)

I rebuilt my benchmark from scratch for the third time. I threw out an entire version, built a Rails app sabotaged with real CVEs, and spent over $4,000 in 9 days. In this Part 1: the process, the cost, and the why.

#llm-benchmarks #llms #coding-agents

Sep 09

You're an Idiot if You Believe the Misleading Ads from OpenAI, Anthropic, NVIDIA. Here's Why

Nvidia and OpenAI declared that AGI has arrived, OpenAI brute-forced a Millennium Problem and threatened a mathematician's career, and an Anthropic employee quit crying Skynet. I take the propaganda apart.

#artificial-intelligence #llms #business

Aug 22

LLM Benchmarks: The latest Deepseek v4, stop asking

I ran the new Deepseek v4 snapshots through the benchmark: Flash jumped from 80 to 90 and Pro from 82 to 91, both Tier A, the cheapest in the pack. I still prefer Kimi K3 and GLM 5.3, and I explain why a close score does not mean an equivalent model.

#llm-benchmarks #llms #coding-agents

Aug 18

Hot Take: Harness, Loop Engineering, Graph Engineering Are Bullshit

I posted that Harness Engineering, Loop Engineering, and Graph Engineering are bullshit to sell consulting hours and courses. Here's my receipt: 30+ public repos, an AI marathon, and a whole benchmark — none of it using any of those 'disciplines'.

#artificial-intelligence #llms #vibe-coding

Aug 16

Understanding Anthropic's AI Watermark: How to Beat It

Claude now stamps everything it writes with an invisible statistical watermark, a requirement of European AI law. How it works, what the AI Act demands, and the rewrite in another LLM that wipes the signal.

#llms #security #law-and-regulation

Aug 15

LLM Benchmarks: Qwen 3.8, GLM 5.3, Gemini 3.7, Grok 4.6

GLM 5.3 scored 94 and closed in on the leading trio. Qwen 3.8 Max jumped from 51 to 92 after it stopped hallucinating the RubyLLM API. Gemini 3.7 Flash scored 93 — after its first run was voided for cheating. And the local 27B Qwen showed that context is now the bottleneck.

#llm-benchmarks #llms #coding-agents

Jul 30

New LLM Benchmark: I Reran Every Test!

I reran the LLM Coding Benchmark with a harder test, three phases, native harnesses, and new tiers. Fable led, Terra tied Sol as the best GPT, and 24 models proved suitable for programming.

#llm-benchmarks #llms #coding-agents

Jul 25

LLM Benchmark: Is Opus 5 Any Good?

Opus 5 scored 95/100 on the Rails benchmark, tying Opus 4.8 and edging Fable 5 by one point. Its API rate is half Fable’s, but this narrow test does not define the best LLM.

#llm-benchmarks #llms #coding-agents

Jul 19

LLM Benchmark: Should I Use the Highest-Scoring Model?

Why the top entry in an LLM ranking is not necessarily the best model, why 90+ is a cluster, and how to use benchmarks without outsourcing your technical judgment.

#llm-benchmarks #llms

Jul 17

LLM Benchmark: Has Kimi K3 Reached Claude Opus Level?

I had Kimi K3 build a chat in Rails 8 on its own: it scored 89/A, beat Opus 4.6, and was a cheaper alternative to Opus 4.8. It still lagged behind in architecture, hardening, and tests.

#llm-benchmarks #llms #coding-agents

Jul 09

LLM Benchmarks: Grok 4.5 and GPT 5.6 Sol

Grok 4.5 entered Tier A with 87, and GPT 5.6 Sol scored 92. Sol beat GPT 5.5 by 92 to 81 in the blind A/B test, but re-auditing brought it down to 85. With cache-read fixed, Opus 4.8 remains the best API balance.

#llm-benchmarks #llms

Jul 06

Frank GO: Playing Go with AI

I built Frank GO as a Sabaki fork with KataGo, bringing together more than 4,700 tsumego, historical games, and 15 of Hikaru’s Go games. Overlays make territory and scoring visible to beginners.

#frank #llms #artificial-intelligence #gaming

Jul 01

LLM Benchmark: Sonnet 5 Fails, Gemini Flash Surprises, Sakana Fugu Almost Reaches Tier A

In the coding benchmark, Sonnet 5 scored 58/100 after calling a nonexistent API, while Gemini 3.5 Flash scored 93/100. Sakana Fugu Ultra landed at 79/100, close to Tier A.

#llm-benchmarks #llms #coding-agents

Jun 24

Why LLMs Will Fail at Your Company

The deliberately speculative thesis is that LLMs amplify processes where people outsource decisions. The proposed alternative is daily cycles of decision, implementation, testing, and review close to the outcome.

#llms #vibe-coding #software-engineering

Jun 16

ai-memory: long-term memory (Karpathy Wiki) and self-improvement (Hermes) for your projects

ai-memory turns agent sessions into a searchable Markdown wiki with hooks, MCP, and handoffs between tools. A Hermes-inspired loop promotes memories with validation, evidence, and optional review.

#ai-memory #coding-agents #llms

Jun 15

The Rio 3.5 LLM Controversy. Plagiarism?

Public evidence indicates that Rio 3.5’s initial checkpoint was a blend of Nex-N2-Pro and Qwen, without credit to Nex. The case points to an attribution failure, not legal plagiarism.

#llms #open-source #law-and-regulation

Jun 14

LLM Benchmark: Kimi v2.7 Code, GLM 5.2, MiniMax M3 Local

In the benchmark, GLM 5.2 scored 87 and Kimi K2.7 Code scored 86. The open MiniMax M3 doesn’t fit in 128 GB, while serious programming still calls for Opus 4.8 or GPT 5.5.

#llm-benchmarks #llms #local-models

Jun 11

LLM Benchmark: Fable 5 and the Anthropic Soap Opera

Fable 5 scored 94/100, practically tied with Opus 4.8, but costs ten times more and redirects sensitive tasks. Since Mythos isn’t auditable, I’m sticking with 4.8.

#llm-benchmarks #llms

Jun 01

LLM Benchmarks - An Update on Grok 4.3, MiniMax v3, and Opus 4.8

In the Rails 8 benchmark, Opus 4.8 keeps the lead at 95/100, while Grok 4.3 and MiniMax M3 finally become usable but remain in Tier B, behind GPT and Opus.

#llm-benchmarks #llms #coding-agents

May 30

Complete Manga Solution: Frank Manga+, Frank Yomik, and the Prettify-Manga Extension

Frank Manga+ brings the MANGA Plus catalog to the desktop, while Prettify improves reading on websites and Kindle, and Frank Yomik adds furigana or translation to Japanese and Korean pages.

#frank-yomik #frank #llms #artificial-intelligence

May 24

I Built a Waybar Widget for Omarchy to Monitor LLM Plan Usage: ai-usagebar

ai-usagebar, a Rust port of claudebar, brings Claude, Codex, Z.AI, and OpenRouter into a Waybar widget or standalone TUI that works in any terminal, including over SSH.

#ai-usagebar #omarchy #developer-tools #llms

May 18

AI Agent Memory: Karpathy LLM Wiki and agentmemory in Practice

Akita compares compaction in Claude Code, Codex, and opencode, explains Karpathy’s LLM Wiki, then tests agentmemory before dropping it over structural bugs and pointing to ai-memory.

#ai-memory #coding-agents #llms

May 04

LLM Benchmarks: DeepSeek Unlocked! Use DeepClaude

I swapped opencode’s harness for Claude Code’s loop through DeepClaude, and DeepSeek V4 Pro rose from 69/B to 89/A in 18 minutes and $3.14. The controller’s multi-turn bug remains.

#llm-benchmarks #coding-agents #llms

Apr 25

LLM Benchmarks: Is It Worth ($$) Mixing 2 Models? (Planner + Executor)

Three rounds show multi-agent doesn’t beat solo Opus 4.7 in opencode, which scored 97/100 in 18 minutes for about $4. GPT 5.4 xHigh with a medium executor saves money but loses 3 points.

#llm-benchmarks #coding-agents #llms

Apr 24

LLM Coding Benchmark (May 2026): DeepSeek v4, Kimi v2.6, Grok 4.3, GPT 5.5

I reaudited 24 LLMs on the same Rails app with RubyLLM: Opus 4.7 and GPT 5.4 tie at 97, GPT 5.5 reaches 96, Kimi and Gemini become Tier A, and DeepSeek V4 Pro reaches Tier A only through DeepClaude.

#llm-benchmarks #llms #coding-agents

Apr 18

LLM Benchmarks Part 2: Is It Worth Combining Multiple Models in the Same Project? Claude + GLM??

I tested seven combinations in Claude Code, opencode, and Codex, but no sub-agent was called. Variance across runs and harnesses keeps solo Opus as the default for greenfield projects.

#llm-benchmarks #coding-agents #llms

Apr 15

Why LLMs Aren't Giving You the Result You Expect | Why I Prefer Claude Code Today

Every week somebody tells me 'I canceled my Claude plan, it just doesn't perform as well as GPT for me.' I've got 500+ hours in Claude Code and Codex, 400k lines generated, and both deliver. The difference isn't the model. It's how people are talking to it.

#llms #coding-agents #communication

Apr 06

Is RAG Dead? Long Context, Grep, and the End of the Mandatory Vector DB

Frontier models went from 200k to 1M tokens of context. Does it still make sense to wire up a whole vector DB stack to do RAG, when you can just grep and dump the entire document into the window?

#llms #software-architecture #databases

Apr 05

Testing Open Source and Commercial LLMs - Can Anyone Beat Claude Opus?

This historical benchmark compared 33 LLMs on a Rails app: Opus, Sonnet, and GLM 5 worked, while Qwen 3.6 35B came close on an RTX 5090 after a fix. The rankings were later revised.

#llm-benchmarks #llms #local-models

Apr 05

Turning YouTube into a Karaoke App | Frank Karaoke

I built a Flutter Android app that overlays live scores on YouTube karaoke videos, using audio filtering and YIN in four modes. It’s fun, but scoring is still experimental.

#frank #llms #artificial-intelligence #audio-and-video

Mar 27

Teaching People to Question the News | Frank Investigator

I built Frank Investigator to compare coverage, track omitted sources, and analyze news in 15 stages with three LLMs. The report flags omissions and reframing, but doesn’t issue final verdicts.

#frank #llms #artificial-intelligence

Mar 16

I Rewrote OpenClaw in Rust. Did It Work? | FrankClaw

I rewrote OpenClaw’s core in Rust as FrankClaw, with 56,586 lines, 7 channels, and fixes for the 7 audited critical vulnerabilities. It handles simple conversations, but complex workflows remain untested.

#frank #llms #artificial-intelligence #rust

Mar 09

Going After Email Fraud | Frank FBI

I built Frank FBI to analyze forwarded emails in six layers, combining authentication, reputation, OSINT, and three LLMs. The result is a self-hosted risk report, with the data under your control.

#frank #llms #artificial-intelligence #security

Mar 05

My First Vibe Code Failure and How I Fixed It | Frank Yomik

How I spent days building a manga speech bubble detection system with OpenCV, threw it all out and rebuilt it in hours with a pretrained model. Lessons on vibe coding, productive failure, and knowing when to change course.

#frank-yomik #frank #llms #artificial-intelligence

Mar 04

I Built a Data Mining System for My Influencer Girlfriend — Tips and Tricks

How I built a Rails 8 + SQLite + Discord bot data mining system for my influencer girlfriend in 3 days, 58 commits, with 40+ tools accessible via LLM tool calling.

#rails #backend #llms

Mar 01

Software Is Never 'Done' — 4 Projects, Life After Deploy, and Why One-Shot Prompting Is a Myth

125 post-production commits across 4 projects in 10 days. Real bugs, real users, real iteration. Why one-shot prompting is a myth and software is never 'done'.

#frank #llms #software-engineering #off-topic

Feb 24

RANT: Did Akita Bend Over for AI??

I have been 'bending over' for AI since 2023. If you only watch out-of-context podcast clips, let me spell it out for you.

#artificial-intelligence #llms #vibe-coding

Feb 23

Vibe Code: I Built a Smart Image Indexer with AI in 2 Days | Frank Sherlock

How I built Frank Sherlock, a local AI-powered image catalog desktop app, in a weekend using Agile Vibe Coding with Claude Code.

#frank #llms #artificial-intelligence #vibe-coding

Feb 20

From Zero to Post-Production in 1 Week - How to Use AI on Real Projects | Behind The M.Akita Chronicles

How 274 commits in 8 days shipped a full newsletter, podcast, blog, and Discord bot to production using Extreme Programming with Claude Code as the pair.

#frank #llms #artificial-intelligence #the-m-akita-chronicles

Feb 09

AI Agents: What Would Be the Best Programming Language for LLMs?

A thought experiment on what a programming language designed for LLM coding agents, rather than human programmers, would look like.

#programming-languages #llms #coding-agents

Feb 08

RANT: Did AI Kill Programmers?

Akita's rant on why AI won't replace real programmers, why the programming bubble already popped, the S-curve ceiling of current LLM architecture, and what actually changes for engineers in the LLM era.

#artificial-intelligence #llms #career #off-topic

Feb 01

Vibe Code: I Built a Markdown Editor From Scratch With Claude Code (FrankMD) PART 2

Part 2 of the FrankMD story: refactoring, i18n, syntax highlighting, tests, and the hard-earned lessons from 30 hours of vibe coding with Claude.

#frankmd #frank #llms #artificial-intelligence

Feb 01

Vibe Code: I Built a Markdown Editor From Scratch With Claude Code (FrankMD) PART 1

How I vibe-coded FrankMD, a self-hosted Markdown editor tailored to my blogging workflow, in three days with Claude Code.

#frankmd #frank #llms #artificial-intelligence

Jan 29

Vibe Code: Which LLM Is the BEST?? Let's Talk for REAL

I ran the same extensive analysis pass through Opus 4.5, GPT 5.2 Codex, Kimi 2.5, Gemini 3 Pro and MiniMax v2.1 on a tiny app, and every single one still left things on the table.

#llm-benchmarks #llms #vibe-coding

Jan 11

AI Agents: Comparing the Top LLMs of 2026 on the Zig Challenge

I put the top commercial and open source LLMs of early 2026 through a nasty Zig + llama.cpp migration challenge to see which ones actually deliver.

#llm-benchmarks #coding-agents #llms

Jan 09

Omarchy 3 - One of the Best Coding Agents Out There: Crush

I used Crush with Claude Opus 4.5 on a Hugo blog and a Zig chat using llama.cpp, CUDA, and Qwen3. It refactored scripts, updated APIs, fixed a segmentation fault, and delivered a working binary for nearly $8.

#omarchy #coding-agents #llms

Jun 18

AGI or Skynet Isn't Coming Anytime Soon

Why the current LLM architecture cannot reach AGI, and why the hype from Big Tech CEOs and media-anointed experts is mostly backroom negotiation noise.

#artificial-intelligence #llms #philosophy #off-topic

May 03

Final Attempt to Train an LLM with LoRA. Cannon Shot, But Missing the Fly.

Renting an 80GB H100 on RunPod to fine-tune Qwen3-32B with a LoRA on Zig 0.14, and discovering that even cannon-class hardware can still miss the target.

#llms #machine-learning #performance

May 03

Teaching the Latest Zig to Your LLM - Training LoRAs (Sort Of)

A hands-on walkthrough of training a LoRA adapter on Qwen3-8B to teach it about Zig 0.14, covering datasets, fine-tuning, vLLM serving, and the limits of the experiment.

#llms #machine-learning #zig

May 02

RANT - LLMs are LOOT BOXES!

Why LLMs for real coding behave like gacha loot boxes, and why every incentive in the industry pushes you to burn more tokens.

#llms #coding-agents #software-engineering #off-topic

May 01

When Do LLMs Fail at Programming? A More Realistic Use Case.

A real-world attempt to build a Zig program using llama.cpp with Gemini 2.5 Pro and Aider, showing where LLMs crumble on new languages and libraries.

#llms #coding-agents #zig

May 01

Rant - Will LLMs Evolve Forever? Demystifying LLMs in Programming

A hype-busting rant on LLM benchmarks, the myth of exponential AI progress, and my hands-on experience showing why Vibe Coding does not work.

#llms #vibe-coding #llm-benchmarks #off-topic

Apr 29

Dissecting an Ollama Modelfile - Tuning Qwen3 for Code

A walkthrough of sampling parameters (temperature, top_p, top_k, min_p, repeat_penalty) and how to build a custom Ollama Modelfile to tune Qwen3 for software development tasks.

#llms #local-models #tutorials

Apr 28

Testing the Newly Released Open Source LLM - Qwen3 (with Aider and Ollama)

First hands-on impressions of Qwen3 running locally via Ollama and remotely via OpenRouter, tested with Aider on real refactoring tasks.

#llm-benchmarks #llms #coding-agents

Apr 28

Destroying the ChatGPT 4o "Personality"

How to disable ChatGPT's pseudo-human chatter and get straight, dry technical answers by tweaking the custom traits settings.

#llms #artificial-intelligence #communication

Apr 27

Testing LLMs with Aider on RunPod - which one to use for code?

Hands-on testing of Qwen2.5 Coder, DeepSeek, Codestral and others with Aider, locally on an RTX 4090 and on RunPod, comparing them against Claude and Gemini.

#llm-benchmarks #llms #coding-agents

Apr 25

Your Own Free Universal Co-Pilot Running Local: AIDER-OLLAMA-QWEN

How to run Aider with Ollama and Qwen 2.5 Coder locally to build a free, universal Co-Pilot alternative that works with any editor.

#coding-agents #local-models #llms

Apr 25

LLM Hello World: Building Your Own Local AI Chat

A hands-on Hello World experiment explaining how LLMs actually work under the hood, building a tiny local chat CLI with Qwen 2.5 Coder running on a single GPU.

#llms #local-models #coding-agents

2026 - October

2026 - September

2026 - August

2026 - July

2026 - June

2026 - May

2026 - April

2026 - March

2026 - February

2026 - January

2025 - June

2025 - May

2025 - April