SteveJS

I have several techniques queued up that attempt to counter it. The distinction in Agents.md is definitely part of it.

Not sure if they will work yet.

I am using lean as part of the prd.md description handed to a coding agent. The definitions in lean compile and mean exactly what I want them to say. The implementation i want to build is in rust.

HOWEVER … I hit something i now call a McLuhen vortex error: “When a tool, language, or abstraction smuggles in an implied purpose at odds with your intended goal.”

Using Lean implies to the coding agent ‘proven’ is a pervasive goal.

I want to use lean to be more articulate about the goal. Instead using lean smuggled in a difficult to remove implicit requirement that everything everywhere must be proven.

This was obvious because the definitions i made in lean imply the exact opposite of everything needs to be proven. When i use morphism i mean anything that is a morphism not only things proven to be morphisms.

A coding agent driven by an llm needs a huge amount of structure to use what the math says rather than take on the implications that because it is using a proof system therefore everything everywhere is better if proven.

The initial way i used lean poisoned the satisficing structure that unfolds during a coding pass.

Amusing this downgraded when it points directly to the word used for the phenomenon: https://en.wikipedia.org/wiki/Blinkenlights

I seem to recall an intel i960 was used to drive leds on at least one model.

Ada Palmer has a great blog post on why Stocism is so appealing to rich folks. Her writing is always excellent.

https://www.exurbe.com/stoicisms-appeal-to-the-rich-and-powe...

Wife’s comment: “Cherries? It needs to be an apple.”

This gets those cases right.

https://github.com/KnowSeams/KnowSeams

(On a beefy machine) It gets 1 TB/s throughput including all IO and position mapping back to original text location. I used it to split project gutenberg novels. It does 20k+ novels in about 7 seconds.

Note it keeps all dialog together- which may not be what others want, but was what i wanted.

My grandmother loved clippy.

Melinda French Gates back when she was Melinda French had a part in Clippy.

“Melinda French (then the fiancée of Bill Gates) was the project manager of Microsoft Bob”

Microsoft Bob is where Clippy was born.

Reference: https://www.artsy.net/article/artsy-editorial-life-death-mic...

The larger project is to allow analyzing stories for developmental editing.

Back in June and August i wrote some llm assisted blog posts about a few of the experiments.

They are here: sjsteiner.substack.com

Also matryoshka and the ability to guide matches by using prefix instructions on the query.

I have ~50 million sentences from english project gutenberg novels embedded with this.

The summer before i took 6.001 i read “The little LISPer”. It is a good intro.

This is the version i read:

https://www.abebooks.com/9780023397639/Little-LISPer-Third-E...

https://en.wikipedia.org/wiki/Ternary_computer

Here is a (3 month old) repo where i did something like that and all the tasks are checked into the linear git history — https://github.com/KnowSeams/KnowSeams

Having the llm write the spec/workunit from a conversation works well. Exploring a problem space with a (good) coding agent is fantastic.

However for complex projects IMO one must read what was written by the llm … every actual word.

When it ‘got away’ from me, in each case I left something in the llm written markdown that I should have removed.

99% “I can ask for that later” and 1% “that’s a good idea i hadn’t considered” might be the right ratio when reading an llm generated plan/spec/workunit.

Breaking work into single context passes … 50-60k tokens in sonnet 4.5 has had typically fantastic results for me.

My side project is using lean 4 and a carelessly left in ‘validate’ rather than ‘verify’ lead down a hilariously complicated path equivalent to matching an output against a known string.

I recovered, but it wasn’t obvious to me that was happening. I however would not be able to write lean proofs myself, so diagnosing the problem and fixing it is a small price to be able to mechanically verify part of my software is correct.

I do like the oddish (half cli / half tui) form factor of these ‘CLI’ coding agents. But i pretty much always pair with vscode for diff viewing.

It is not llm specific. A large swathe of it isn’t that much Microsoft specific either.

And it is a developer feature hidden from end users. e.g. - In your ollama example, does the developer ask end users to install ollama? Does the dev redistribute ollama and keep it updated?

The ONNX format is pretty much a boring de-facto standard for ML model exchange. It is under the linux foundation.

The ONNX Runtime is a microsoft thing, but it is an MIT licensed runtime for cross language use and cross OS/HW platform deployment of ML models in the ONNX format.

That bit needs to support everything because Microsoft itself ships software on everything.(Mac/linux/iOS/Android/Windows.

ORT — https://onnxruntime.ai

Here is the Windows ML part of this —https://learn.microsoft.com/en-us/windows/ai/new-windows-ml/...

The primary value claims for Windows ML (for a developer using it)— This eliminates the need to: Bundle execution providers for specific hardware vendors

Create separate app builds for different execution providers

Handle execution provider updates manually.

Since ‘EP’ is ultra-super-techno-jargon:

Here is what GPT-5 provides:

Intensional (what an EP is)

In ONNX Runtime, an Execution Provider (EP) is a pluggable backend that advertises which ops/kernels it can run and supplies the optimized implementations, memory allocators, and (optionally) graph rewrites for a specific target (CPU, CUDA/TensorRT, Core ML, OpenVINO, etc.). ONNX Runtime then partitions your model graph and assigns each partition to the highest-priority EP that claims it; anything unsupported falls back (by default) to the CPU EP.

Extensional (how you use them) • You pick/priority-order EPs per session; ORT maps graph pieces accordingly and falls back as needed. • Each EP has its own options (e.g., TensorRT workspace size, OpenVINO device string, QNN context cache). • Common EPs: CPU, CUDA, TensorRT (NVIDIA), DirectML (Windows), Core ML (Apple), NNAPI (Android), OpenVINO (Intel), ROCm (AMD), QNN (Qualcomm).

The content is good. I’m glad i ignored a similar negative reaction to the reverse engineering framing.

Those are Jaz’s daily unique action counts (flows) from the Bluesky firehose; they’re anchored to the Nov ’24 spike, so the ‘decline’ is post-surge reversion. Meanwhile the user stock kept rising (~39M).

A presidential election spike is the baseline for tracking growth in a social media platform??

I zoomed out. It looks like this: "Usage has absolutely declined from peak switching periods where inevitibly some users won't stick around, but that's to be expected"

That just isn't a "sharp decline" no matter how much you seem to want to repeat those words.

Personas are a great tool. IMO - By the time you arrived these had transformed into bad shorthand. (I say this having been in Devdiv through those years.)

Elvis is not a persona - it is an inside baseball argument to management. It suffered a form of Goodhart’s law … it is a useful tool so people phrase their arguments in that form to win a biz fight and then the tool degrades.

Alan Cooper, who created VB advocated personas. When used well they are great.

The most important insight is your own PoV may be flawed. The way a scientist provides value via software is different than how a firmware developer provides value.

https://www.amazon.com/Inmates-Are-Running-Asylum/dp/0672316...

Was trying to remember a counter example on good hires and wasted money.

Alex St. John Microsoft Windows 95 era, created directX annnnd also built an alien spaceship.

I dimly recalled it as a friend in the games division telling me about some someone getting 5 and a 1 review scores in close succession.

Facts i could find (yes i asked an llm)

5.0 review: Moderately supported. St. John himself hosted a copy of his Jan 10, 1996 Microsoft performance review on his blog (the file listing still exists in archives). It reportedly shows a 5.0 rating, which in that era was the rare top-box mark. Fired a year later: Factual. In an open letter (published via GameSpot) he states he was escorted out of Microsoft on June 24, 1997, about 18 months after the 5.0 review. Judgment Day II alien spaceship party: Well documented as a plan. St. John’s own account (quoted in Neowin, Gizmodo, and others) describes an H.R. Giger–designed alien-ship interior in an Alameda air hangar, complete with X-Files cast involvement and a Gates “head reveal” gag. Sunk cost before cancellation: Supported. St. John says the shutdown came “a couple of weeks” before the 1996 event date, after ~$4.3M had already been spent/committed (≈$1.2M MS budget + ≈$1.1M sponsors + additional sunk costs). Independent summaries repeat this figure (“in excess of $4 million”).

So: 5.0 review — moderate evidence Fired 1997 — factual Alien spaceship build planned — factual ≈$4M sunk costs — supported by St. John’s own retrospective and secondary reporting

AFAICT, the RTX 4090 I bought in 2023 has actually appreciated rather than depreciated.

Nah it was a hobby project because I was laid off for a bit.

Rust's RegEx was perfect because it doesn't allow anything that isn't a DFA. Yes-ish, the LLM facilitated designing the state machine, because it was part of the dev-loop I was trying out.

The speed is primarily what enabled finding all of the edge cases I cared about. Given it can split 'all' of a local project gutenberg mirror in < 10 seconds on my local dev box I could do things I wouldn't otherwise attempt.

The whole thing is there in the ~100 "completed tasks" directory.

I think this is true -- especially for new code.

I did this not knowing any rust: https://github.com/KnowSeams/KnowSeams and rust felt like a very easy to use a scripting language.

I made this to try out Claude code. I have the $17/mo thing, and i don’t know rust. (I do know plenty of other languages.) Rust felt like a scripting language when used this way. I used a task system to force getting to a git commit before auto-compact. The completed tasks are in the repo allowing one to see what starting context kicked off the changes. It worked much of the time. It’s 8k of rust, 12k of markdown and i think the markdown helps to correctly interact with a codebase using agents just as unit tests assist in refactoring. On my I9 with a local gutenberg mirror this e2e discovers 20k+ english novels, splits them into sentences, normalizes the sentences, keeps the origination text span and writes it out as tsv’s. It takes 7 seconds to complete that for 7 Gb of novels. Most importantly it splits the sentences the way i needed for the start of my pipeline.

Definitely interested if anyone find cases where it mis-splits english text from a novel.

I used it for 2 weeks with the cheap $17/mo sub. It is equal parts amazing, and frustrating.

I ended up with 8k lines of rust and 12k lines of markdown. I think those markdown designs and explicit tasks were required the same way unit tests with a test harness are required to make the human-tool interaction work.

However, I’m not sure if the ‘magic’ is VC-subsidy or something else.

It did make rust (a language i do not know) feel like a scripting language. … the github repo is ‘knowseams’.

I loved discovering that rust has O(n) guardrails on regex! The so-called features that break that constraint are anti-features.

Over the last two weeks I wrote a dialog aware english sentence splitter using Claude code to write rust. The compile error when it stuck lookarounds in one of the regex’s was super useful to me.

Is there firmware to turn the Bose Alexa into just a Bluetooth speaker? I see there is a bose-dfu utility on github, but its list of supported devices is short (because the person who made it didn’t have other devices).

The bose speaker is sufficiently nice i might try to salvage it.

I really did like that kitchen timer. This seems like it would have been pretty good.

However. My wife is super pissed at Bezos. She unplugged all our echos. She has me researching to try decide between a Roku or Apple tv to replace the fire tv.

The amazon card went from 90% of our non-mortgage spending to 10% and dropping.

I honestly didn’t believe it would ever happen but I think we are probably going to drop Prime soon.

I’m still thankful for the Expanse, that show was great.

Pointed a friend toward this. He thought it was cool, but said he’d never wear a Cray wristwatch because he heard they run fast.

there’s a quote at the end, saying this establishes a fundamental connection between two objects which are central to computer science.

The quote leaves those two objects unnamed. Are they supposed to be “graphs” and “groups”?