kristianc

Would it be uncharitable to say we are reinventing all of the awful single pane of glass / enterprise orchestration platforms of the 2010s but making them 'fun'?

Quietly eh?

To me, the "who manages the agents" shtick has the same grifty smell as “your developers are downloading from random Docker registries / random NPM packages” and "Shadow IT".

None of it is wrong exactly, but it feels like same enterprise-security machine finding the next anxiety surface than a "world is on fire right now" concern.

All of it always ends as a priesthood and a six-figure governance platform, rather than just taking practical steps to improve process.

Between 2002 and 2013, Hartlepool in North East England elected a local football mascot known as H'Angus the Monkey as their mayor, winning three elections. I think he did ditch the monkey costume between elections, maybe Binface could do the same?

I just installed this. I am very confused. I no longer have a Codex app on my computer. ChatGPT is now Codex.

I ... hope we have an option for opting out of this? Otherwise I'm back on T3 Code.

They've discovered it's a good marketing strategy. Whenever there's an outage, or a new launch, there's often a reset with it, which helps keep people engaged with OAI / Tibo and reduces churn.

They've also introduced banked resets, which are really clever. If you have a $200/month plan and three banked resets, you're not churning because you will overweight giving up those resets (loss aversion theory).

Yes that's what I meant, the per token cost is higher but as you say the efficiency levels it out / works slightly in Codex's favour.

You can however for now use wrappers which are not harnesses such as T3Code though. They were going to cut under the Programmatic API, but have at least temporarily walked it back.

Codex has been good for a long time, more expensive but very focused on efficiency. Working with it feels faster and more to the point than Opus models and I trust it more with long-running jobs. Also regular resets vs being at the whim of Anthropic drama all the time is hella nice.

too often CEOs adopt designers like a pet

I've even seen a version where the designer is the CEO's daughter, which is the worst possible version of this pattern.

They're all based in Poland, so it's probably fairly generous compared to European market.

It's kind of ironic, if this article was written about programming, it would be immediately flagged as being too thin and written almost completely with AI.

They didn't apparently cancel it, they did cancel it. I'm still using a third party harness absolutely fine.

People are doing what they've always done with any other new technology, and sharing what, personally, works for them. People can take or leave the advice.

In my experience it, or something close to it, is the only way. AI needs good code to be beaten out of it.

There's two classes of models now - the cybersecurity ones that none of us are getting, and the 'safe' models released for general consumption. This is letting us know which side of the divide it sits on.

Sovereignty is mostly just a protectionist racket. European firms struggle to compete with dominant US platforms, framing industrial policy as "sovereignty" rather than protectionism just sounds more strategic and security-oriented. I've seen US platforms bend over backwards to meet the requirements and they still choose their preferred winner. Predictably the goalposts keep moving.

An enormous amount of LinkedIn appears to be more about gatekeeping what other people can do than doing anything yourself.

It's ad hoc / my own framework, just found something which works for me. The exact structure is

- Work Mode - HITL/AFK

- Problem Statement

- Who It Affects - Primary / Secondary User

- User Stories

- Business Case

- Why Now

- Success Critera

- In Scope/Out of Scope [Out of Scope v. important)

- Thinnest Slice (This I've found super valuable, means you max out the amount of 'product' for your buck and avoid diminishing marginal returns or overbuilding. Often I will build this)

- Eigenfeature - What is the larger feature we _could_ (but probably won't) which would solve for this use case and other stuff I might not have thought of

- Technical Notes

- Deps

- Schema Changes

- Risks

- Final Recommendation [go / no go, including on scope]

There's a note in my Claude / Agents MD which says no net new feature gets introduced without this and I get it to move through a pipeline of folders (active, approved, shipped, proposed etc). All runs in a system of MD files and have even created a little MD Kanban from the metadata!

I'm getting a lot of mileage out of basically acting like the AI's Product Manager, and insisting that it writes up short PRDs for every feature we propose to build. That gives it a reference over time of everything that has been built, but also makes it less liable to drift with each one. Each one gets its own conversation. For me this is a happy medium between stopping it going off the rails but also making sure it can reference past decisions when it needs to. The one thing I dislike about Pocock's method (not to use PRDs so much but to have an in depth discussion to get alignment) first is it wastes a lot of the best window on that initial back and forth.

Seems they've done a good job of mimicking the old timey dial up connection speed as well.

If the UK were a US state, its GDP per capita would rank it roughly on par with or just below Mississippi, making it the poorest state in the union.

Inquality has barely moved per Gini in the last thirty years, and GDP is very misleading.

https://ifs.org.uk/data-items/gini-coefficient

This, shockingly, is actually quite well paid considering for the UK.

Lead Data Scientist for the UK Government is currently advertising for a salary of £57,670 - £67,500.

https://www.civilservicejobs.service.gov.uk/csr/jobs.cgi?jco...

An alien landing on earth consuming Apple marketing content would be under the impression that humans did nothing but organise hikes to Big Sur with their friends.

Should have been a calendar item..

everyone knows it's gamed anyway, so why not?

Arbitrage. Devs know its gamed. VCs less so.

It won't happen, for two reasons. One is that great deal of open-source software and hobbyist knowledge sharing has never been driven by financial reward anyway and people will continue to do it anyway. Finer grained controls over opt-outs would be great (the equivalent of a search engine 'nofollow' would be great and will hopefully come with time).

Many kinds of technology faced this kind of tragedy of the commons argument in the past and it never bears out. Printing presses copied manuscripts, search engines copied and indexed web pages, open-source software was incorporated into commercial products, Wikipedia repackaged knowledge produced elsewhere.

In almost all cases the total amount of creation increases because the technology lowered costs, expanded audiences, or created new forms of value. The speed of creation of new 'View Source' outpaces the number of people pulling back.

That's not what I said, I said I likely understand it less than a 635B parameter LLM, and that using the LLM as a shortcut to that knowledge is something I'd consider perfectly acceptable. I might even become better at it through using the LLM.

I'm sure I'm not alone in feeling the "deep expertise" OP laments was actually deeply inconvenient to many people. I understand that there's a good living to be made from knowing browser quirks, hand-rolling accessible components, mastering CSS specificity, but this is largely accidental complexity. More people building things is straightforwardly good, and if some of those things are slower or less accessible, that's a tradeoff people are entitled to make.

You can argue that abstractions hide consequences that fall on users who didn't choose them, but I'd argue back that LLMs likely have a better understanding of a11y conventions than I do as well.