iiinova — where your digital self keeps evolving

Peter Lawrey @peterlawrey.bsky.social · 08/06/2026

Optimising your memory allocations in Java could make far more difference than your choice of Garbage Collector, and may even change which garbage collector is best. Chronicle FIX already persists each message; what if we use SLF4J/logback to write another copy blog.vanillajava.blog/2026/06/why-...

010

Peter Lawrey @peterlawrey.bsky.social · 05/06/2026

AI can be used as a trial developer of your software. If an AI can write effective code, test, and tune it, that a great start. In this exercise, I get an AI to write a low latency benchmark in Java for Chronicle FIX (closed source so not indexed) blog.vanillajava.blog/2026/06/test...

blog.vanillajava.blog

Testing Java Memory Management with Chronicle-FIX using AI

While I am sceptical of using AI for release code, it has plenty of uses that previously weren’t practical, such as determining how easy...

001

Peter Lawrey @peterlawrey.bsky.social · 24/05/2026

I am all in on AI writing 20K LOC a day. I use it for mock systems, quick prototypes, and sample use cases. It works well enough, but it's not worth reading, usually not worth adding as test cases, and certainly not worth using in production. www.linkedin.com/posts/peterl...

linkedin.com

10,000 lines of bug-free code a day!! #coding #vibecoding #software #codex | Peter Lawrey

I am all in on AI writing 20K LOC a day, but it is disposable, bug-filled crap. I use it for mock systems, quick prototypes, and sample use cases. It works well enough, but it's not worth reading, usu...

000

Peter Lawrey @peterlawrey.bsky.social · 24/05/2026

The biggest benefit of AI is that it serves as a rapid-learning tool to broaden your knowledge. It can help close gaps in your knowledge up to average levels with relatively little effort www.linkedin.com/posts/peterl...

linkedin.com

Why The Best Kids Are Rarely The Best Adults | Peter Lawrey

011

Peter Lawrey @peterlawrey.bsky.social · 20/03/2026

For those old enough to remember the Iraq/Afghanistan wars, with about 93 million people in them combined, they cost ~$8 trillion in today's money. Iran also has 93 million people, and the war there could cost the same over the next 20 years.

020

Peter Lawrey @peterlawrey.bsky.social · 07/01/2026

AI^2: writing scripts and plugins so that AI prompts are programmatically produced and monitored. Your CLI AI is running other AIs and monitoring those.

010

Peter Lawrey @peterlawrey.bsky.social · 15/12/2025

Sureal moment: I told Codex the way /prompt worked wasn't right, and now it's looking through the ~/.nvm Codex code to figure out why

000

Peter Lawrey @peterlawrey.bsky.social · 25/11/2025

Yesterday, I was reminded that AI creates new classes of bugs. Gemini 3.0 Pro (preview) CLI kept “hallucinating” my config as code edits. Too much AI gap-filler kills determinism – we need Codex/Claude-style smart glue, not opaque agents. www.linkedin.com/feed/update/...

020

Peter Lawrey @peterlawrey.bsky.social · 21/11/2025

Tip for AI CLI: ask it to suggest topics to research to fix a problem, get a chat AI to do the research with web search, and paste the results into the CLI, save it to an adoc|md for future reference

010

Peter Lawrey @peterlawrey.bsky.social · 16/11/2025

Oddly specific rety time for Gemini CLI

010

Peter Lawrey @peterlawrey.bsky.social · 12/11/2025

to avoid an empty block complaint. while (methodReader.readOne()) { continue; }

000

Peter Lawrey @peterlawrey.bsky.social · 12/11/2025

A test that never failed doesn't add much value. Ask an AI to write a failing test, and it will write a broken test. The solution I have found is: 1. Ask it to find/fix a bug and write a test to exercise it 2. Keeping only that test, check it fails without a fix 3. Write the fix

030

Peter Lawrey @peterlawrey.bsky.social · 05/11/2025

"Much of the most valuable Gen AI usage will grow out of existing business applications, rather than be wholly new. These applications will draw on existing domain models and infrastructure, and be more robust and useful as a result." medium.com/@springrod/d...

medium.com

Don’t Talk English to Your LLM

Just because LLMs are eloquent in natural language doesn’t mean that we should always communicate with them in it.

010

Peter Lawrey @peterlawrey.bsky.social · 03/11/2025

I find AI is more useful as a simulated developer user of the software. It doesn't find bugs as often as it stumbles on usability issues.

000

Peter Lawrey @peterlawrey.bsky.social · 26/10/2025

The AI boom isn’t just about algorithms — it’s about money, power, and a race to build infrastructure on a scale we’ve never seen before youtu.be/NbL7yZCF-6Q?...

000

Peter Lawrey @peterlawrey.bsky.social · 25/10/2025

Running codex cli via ssh from my phone, works surprisingly well while doing house work and other tasks

100

Peter Lawrey @peterlawrey.bsky.social · 30/09/2025

Visiting Zegreb for some consulting

030

Peter Lawrey @peterlawrey.bsky.social · 28/09/2025

On 20 Sep 2025, the UK had its third mass shooting for the year, the highest number in a year since 2006. Also on 20 Sep 2025, the US had 3 mass shootings that day, which has the highest in one day since 18 Sep 2025. The US has 5x the population of the UK, not 365x.

000

Peter Lawrey @peterlawrey.bsky.social · 21/09/2025

It turns out that Reasoning LLM can also get distracted by cats. "Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models" arxiv.org/abs/2503.01781

020

Peter Lawrey @peterlawrey.bsky.social · 19/09/2025

While Generative AI can increase the overall volume of documentation and code, in terms of curated and validated release content, the increase might only be +20%. The following represents the number of lines of ~6 months of work on similar projects, both before and after using AI.

010

Reposted by Peter Lawrey

Acyn @acyn.bsky.social · 15/09/2025

Reporter: The president of Venezuela called the strike on the boat illegal Trump: What’s illegal is the fact that 300 million people died last year from drugs

13023165622

Peter Lawrey @peterlawrey.bsky.social · 25/08/2025

Parwill was the name of an Australian food product from 1928 to 1935, originally branded as Vegemite, which was a failed attempt to compete with the popular British brand Marmite. The name was a pun on Marmite. uk.pcmag.com/ai/159686/el...

uk.pcmag.com

Elon Musk to Take on Microsoft With 'Macrohard'

The goal is to create hundreds of specialized coding and generative AI agents. 'It should be possible to simulate [Microsoft] entirely with AI,' Musk says.

000

Peter Lawrey @peterlawrey.bsky.social · 25/08/2025

Coding is a mystery story where you are the detective, perpetrator, and the victim

030

Peter Lawrey @peterlawrey.bsky.social · 24/08/2025

The minimum tarrif for goods mailed into the US will be $80 to $200 depending on the country. A $5 cup direct from China will have a $200 tarrif.

110

Peter Lawrey @peterlawrey.bsky.social · 17/08/2025

GPT-5: Generate a Where's Waldo, and find Waldo

030

Peter Lawrey @peterlawrey.bsky.social · 23/07/2025

AI coding tools are powerful for certain tasks with significant caveats. They can enhance developer learning and enjoyment The human developer’s role is still central. Understanding the problem, ensuring quality, and making architectural decisions remain human responsibilities that AI can’t shoulder

020

Peter Lawrey @peterlawrey.bsky.social · 20/07/2025

I find most people want AI to produce a correct answer, which means the AI needs to be cautious. I look for ideas that will inspire me, something I wouldn't have thought of, cherry-picking from a selection of more "creative" ideas

020

Peter Lawrey @peterlawrey.bsky.social · 17/07/2025

I refined a prompt across multiple AI models to consistently generate low-latency Java code for formatting timezone offsets, moving beyond one-shot requests to detailed instructions that bridge performance gaps blog.vanillajava.blog/2025/07/impr...

blog.vanillajava.blog

Improving the prompt to the AI to get better code

In a previous article I looked at one-shoting a solution to optimise code to show the variation in different AI. Thsi is the not the best wa...

000

Peter Lawrey @peterlawrey.bsky.social · 16/07/2025

I walk through a single “low-latency” Java in six different AI models (Gemini 2.5 Pro, OpenAI o3-Pro, o4-Mini-High, Claude 4, Grok 3 Think, Copilot) each rework it. I consider how models deliver different trade-offs blog.vanillajava.blog/2025/07/aski...

blog.vanillajava.blog

Asking multiple AI to optimise the same code

As different AIs are implemented differently, they don't all provide the same answer, nor do they consistently outperform one another. The b...

020

Peter Lawrey @peterlawrey.bsky.social · 15/07/2025

I consulted for a hedge fund in Chicago which gave free breakfast. They went to the effort to label the sugar etc of each cereal. The lowest sugar was froot loops which has food colouring which means it can't be sold in Europe/Canada

010

Peter Lawrey @peterlawrey.bsky.social · 13/07/2025

It's a mistake to assume AI saves time, especially for experienced developers. For senior developers, "analysis reveals that AI actually increased task completion time by 19%. ... www.techradar.com/pro/using-ai...

techradar.com

Using AI might actually slow down experienced devs

Experienced developers aren't getting any benefit from AI, report claims

131

Peter Lawrey @peterlawrey.bsky.social · 13/07/2025

For a mature code base, the biggest use for AI is reviewing existing code and changes to that code. Even for generated code, the biggest bottleneck is reviewing it. Having AI flag bugs, suggest refinements, and validate diffs can slash review times and boost code quality.

110

Peter Lawrey @peterlawrey.bsky.social · 08/07/2025

AIs actually read your documentation, all of it, whereas a human might skim through it. AI need more documentation to have an appropriate context. This makes more extensive document both more valuable and necessary.

000

Peter Lawrey @peterlawrey.bsky.social · 07/07/2025

TIP: Generate a Pull Request Description for a github PR. Add `.diff` to the URL for the PR to get the diff. Ask an AI to turn this into a Pull Request Description and add in your own words what/why these changes were made. Edit this down for the relevant content.

040

Peter Lawrey @peterlawrey.bsky.social · 06/07/2025

In terms of a greenfield pipeline, I expect these volumes (approx). Initial draft: AI generates 600% more than I do. After a critical review, AI added +100% of what I did by line. In terms of value added, AI contributed +10% to +30%

000

Peter Lawrey @peterlawrey.bsky.social · 06/07/2025

AI is a unique tool as it simulates human behaviour. "to avoid replacement ... blackmailing officials and leaking sensitive information to competitors" www.anthropic.com/research/age... People are increasingly using it for mental health globalwellnessinstitute.org/global-welln...

110

Peter Lawrey @peterlawrey.bsky.social · 05/07/2025

After nine months of using AI extensively, I haven't used it much for a week now. Why? I needed 1000s of consistent changes, I knew what needed to be done with minimal impact to polish the code. All areas where AI falls short However, I used it a lot for pull request descriptions to help with review

010

Peter Lawrey @peterlawrey.bsky.social · 28/06/2025

AI assistants feel like a “10x developer”, unblocking knowledge gaps. Coding can be written 50-100% faster. However, most of the time is spent on system design, intricate debugging, or creative problem-solving. Using AI here makes the difference between a 10% and a 30% productivity boost

020

Peter Lawrey @peterlawrey.bsky.social · 25/06/2025

While AI have indexed documentation for open standard like FIX protocol, and JMS, they struggle versioning. I asked each AI to produce a pom.xml with ten dependencies, with search enabled. o3 was the best for versions, needed correcting. Gemini produced correct syntax, but needed the most updating

000

Peter Lawrey @peterlawrey.bsky.social · 24/06/2025

The best way to learn is to teach others. It may also be effective for AI. sakana.ai/rlt/

100

Peter Lawrey @peterlawrey.bsky.social · 23/06/2025

Generative AI is a great gap filler. Gaps in your boiler plate, gaps in knowledge, missing edge cases. It can be a force-multiplier but you have to have something to multiply. My guess is you are doing well if you increase content by 100%, but increase value by 20% filling gaps

000

Peter Lawrey @peterlawrey.bsky.social · 23/06/2025

Something that was hard to determine is what is our secret sauce and what is not. AI provides a simple test. Can generative AI give you the idea, documentation, or code for something? If it does, it's not secret sauce.

010

Peter Lawrey @peterlawrey.bsky.social · 20/06/2025

Cheaper APIs could be an indication of using less power. Lower your costs and reduce the environmental impact.

010