thomasfromcdnjs

I run 3-5 on distinct projects often. (20x plan) I quite enjoy the context switching and always have. I have a vanilla setup too, and I don't use plugins/skills/commands, sometimes I enable a MCP server for different things and definitely list out cli tools in my claude.md files. I keep a Google doc open where I list out all the projects I'm working on and write notes as I'm jumping thought the Claude tabs, I also start drafting more complex prompts in the Google doc. I've been using turbo repo a lot so I don't have to context switch the architecture in my head. (But projects still using multiple types of DevOps set ups)

Often these days I vibe code a feedback loop for each project, a way to validate itself as OP said. This adds time to how long Claude takes to complete giving me time to switch context for another active project.

I also use light mode which might help others... jks

neopets was definitely a factor, who else? And "hacking" school computers, windows use to let you make folder backgrounds with html, could do some funny stuff.

I have been telling everybody I know over the Christmas break that I have been coding from around 10-36 years of age, as a career and always in my spare time as a hobby. I have a lacklustre computer science knowledge and never worked at the scale of FANG etc but am still rather confident in my understanding of code and the tech scene in general. I've been telling people I haven't "coded" for almost 6 months now, I only interface with agentic setups and only open my IDE to make copy and config changes.

I understand we are all in different camps for a multitude of reasons;

- The jouissance of rote coding and abstraction

- The tree of knowledge specifically in programming, and which branches and nodes we each currently sit at in our understanding

- Technical paradigms that humans may have argued about have now shifted to obvious answers for agentic harnesses (think something like TDD, I for one barely used that as a style because I've mostly worked in startups building apps and found the cost of my labour not worth it, but agentic harnesse loops absolutely excel at it)

- The geography and size of the markets we work in

- The complexity of the subject matter / domain expertise

- The cost prohibitive nature of token based programming (not everyone can afford it, and the big fish seemingly have quite the advantage going fourth)

- Agentic coding has proven it can build UI's very easily, and depending on experience, it can build a very very many things easily. it excels in having feedback loops such as linting or simple javascript errors, which are observability problems in my opinion. Once it can do full stack observability (APM, system, network), it's ability to reason and correct problems on the fly for any complex system seems overly easy from my purvue.

- At the human nature level, some individuals prefer to think in 0's and 1's, some in words, some inbetween, and so on, what type of communication do agentic setups prefer?

With some of that above intuition that is easily up for debate, I've decided to lean 100% into agentic coding, I think it will be absolutely everywhere and obviously with humans in the loop but I don't think humans will need to review the pull requests. I am personally treating it as an existential threat to my career after having seen enough of what it's capable of. (with some imagination and a bit of a gambling spirit, as us mere mortals surely can't predict the future)

With my gambit, I'm not choosing to exit the tech scene and instead optimistically investing my mental prowess into figuring out where "humans in the loop" will be positioned. Currently I'm looking into CI level tooling, the known being code quality, and all the various forms of software testing paradigms. The emerging evals in my mind will keep evolving and beyond testing our ideas of model intelligence and chat bot responses will do a lot more.

---

A more practical rant: If you are building a recommendation engine for A and B, the engine could have X amount of modules that return a score which when all combined make up the final decision between A and B. Forgive me but let's just use dating as an example. A product manager would say we need a new module to calculate relevance between A and B based off their food preferences. An agentic harness can easily code that module and create the tests for it. The product manager could ask an LLM to make a list of 1000 reasons why two people might be suitable for dating. The agent could easily go away and code and test all those modules and probably maintain technical consistency but drift from the companies philosophical business model. I am looking into building "semantic linting" for codebases, how can the agent maintain the code so it aligns with the company's business model. And if for whatever reason those 1000 modules need to be refactored, how can the agent maintain the code so it aligns with the company's business model. Essentially trying to make a feedback loop between the companies needs and the code itself. To stop the agent and the business from drifting in either directions, and allowing for automatic feedback loops for the agent to fix them. In short, I think there will be new tools invented that us human's will be mastering as to Karpathy's point.

hey hey,

I currently use ai sdk by the vercel team heavily, thought it would be nice to have a registry for all tools as a matter of convenience with a few added goodies. Currently, it is simply an npm mirror where package authors can set a top level property in their package.json called "tpmjs" which flags it to be picked up by tpmjs. Beyond just simply being a directory, I've also added an executor playground which is currently free to use (and open source) which makes it very simple to just add the tpmjs search and execute tool to your agent's which allows them to take advantage of all listed tools without installing any of them locally in your own codebase. (sounds horrible I know but if you play around with the idea enough it could actually make sense if you hosted everything yourself)

if you play around with https://playground.tpmjs.com the thing to note is, is that app does not have any of those tools compiled in, it is using the external executor at runtime. It fetches via esm.sh and runs it inside a sandboxed deno which returns the results to your agent.

currently will be reaching out to tool authors to get their feedback on adding the "tpmjs" property to their package.json

all feedback is welcome

Thanks will fix that up shortly.

shameless plug: I'm working on an open source project https://blocksai.dev/ to attempt to solve this. (and just added a note for me to add formal verification)

Elevator pitch: "Blocks is a semantic linter for human-AI collaboration. Define your domain in YAML, let anyone (humans or AI) write code freely, then validate for drift. Update the code or update the spec, up to human or agent."

(you can add traditional linters to the process if you want but not necessary)

The gist being you define a bunch of validators for a collection of modules you're building (with agentic coding) with a focus on qualifying semantic things;

- domain / business rules/measures

- branding

- data flow invariants — "user data never touches analytics without anonymization"

- accessibility

- anything you can think of

Then you just tell your agentic coder to use the cli tool before committing, so it keeps the code in line with your engineering/business/philosophical values.

(boring) example of it detecting if blog posts have humour in them, running in Claude Code -> https://imgur.com/diKDZ8W

I have Linear(mcp) connected to ChatGPT and my Claude Desktop, and I use it daily from both.

For the MCP nay sayers, if I want to connect things like Linear or any service out there to third party agentic platforms (chatgpt, claude desktop), what exactly are you counter proposing?

(I also hate MCP but gets a bit tiresome seeing these conversations without anyone addressing the use case above which is 99% of the use case, consumers)

"bad press is good press"

I don't care for Zig at all, and had never heard of Codeberg, they are now solidified in my mind aha

To piggy back on this, as a thought experiment, if you took all the wealth of every American billionaire combined you would pay for the US government for about a year.

ha I thought it was just a me thing and had have accepted my fate.

You are really speaking to others points. Get a friend of yours to read what you are saying, it doesn't sound scientific in the slightest.

Sounds better suited for a "Political Mode"

So people who want/ask a lot of politics, they can switch into this mode, and give feedback on it and try to improve it.

My two cents is that peoples personal politics is never swayed by "knowledge" anyway, just by the experiences they gather throughout life, age and the march towards death being front and center.

Most people will just seek to confirm bias where ever they feel like, the few who seek deeper understanding and facts will just have to persevere as they always have done, hence why sometimes throughout history we greatly respect that archtype.

I feel like I've seen good solutions to both problems before, aren't there vscode extensions that let you just select the code and create a sharable link with all the view type options to appear everyone?

e.g. https://snippetshare.dev/

Find a codebase that you wrote that you enjoy, ask Claude to analyse it and write an agents.md based off of it.

* Location: Melbourne, Australia

* Remote: Yes

* Willing to relocate: Yes - Worldwide

Technologies: 20 years of experience, mostly Javascript. I've coded in pretty much all non functional languages though. Most of the databases sql/nosql. Comfortable with gCloud/aws/heroku etc. Mostly worked with node/rails/laravel/python/golang backends.

* Résumé/CV: https://registry.jsonresume.org/thomasdavis

* GitHub: https://github.com/thomasdavis/

I'm a full stack web developer who can build apps from the ground up. I've worked mostly at startups so I am used to wearing many hats. I am a very product focused developer who prioritizes user feedback first and foremost. I'm generally very flexible when investigating new roles. Nothing too big or small.

Agreed.

I've played around with agent only code bases (where I don't code at all), and had an agent hooked up to server logs, which would create an issue when it encounters errors, and then an agent would fix the tickets, push to prod and check deployment statuses etc. Worked good enough to see that this could easily become the future. (I also had it claude/codex code that whole setup)

Just for semantic nitpicking, I've zero shot heaps of small "software" projects that I use then throw away. Doesn't count as a SAAS product but I would still call it software.

Just fyi, they don't put vinegars at the beaches anymore, apparently it makes it worse (well I haven't seen any for a long while)

https://www.abc.net.au/news/2014-04-08/vinegar-makes-box-jel...

A little nostalgic for me, I wrote a bunch of backbone tutorials back in the day.

https://news.ycombinator.com/item?id=3110025 https://web.archive.org/web/20111015073638/https://backbonet...

Other than the lack of imports, 15 years later I don't hate it.

Due to LLM's my thinking about coding has changed quite a bit, I'm far more interested in what is the best way a language can be written such that LLM's can most effectively write it. JSX/declarative is seemingly solid. I think the React community from useEffect onwards is starting to get a bit wishy washy, probably not a great way for LLM's to "think". (something about expressiveness, explicitness and parse-ability)

I know everyone in thread today is having fun embracing the hacker ethos and running things themselves.

But I've migrated plenty of companies off custom deployment setups to PAAS and told many ceo's simply what OP above has shared. Even a part time dev ops engineer is still $60000 a year, and that can buy us a LOT on PAAS. Using PAAS you can have effectively zero dev ops, I've also trained non technical people on how to scale their own servers if no devs are around because you just have a web based UI slider.

I consider myself a developer who cares more about the business, risk, profits and runway. A lot of developers don't share this mentality (which is fine btw always need engineers who like engineering for engineering sakes) but in meetings you will have a hard time beating me in an argument if you try to say that running servers ourselves would be "cheaper", and/or even faster, safer and definitely not more stable. (obviously not in all situations, but kind of most for modern crud web apps that don't require complicated compute setups)

I'm probably being overly antagonistic, forgive me for that, though highly recommend questioning the real cost of running your own setups.

You might get better results with https://github.com/oraios/serena

I sometimes use it, but I've found just adding to my claude.md something like "if you ever refactor code, try search around the codebase to see if their is an existing function you can use or extend"

I never understand why people don't talk about banning the general usage of sugar, probably has far worse effects on societal systems than smoking does. (attention, fatness, hormonal imbalances)

Was already struggling to do any work today and now my builds aren't working.

https://xkcd.com/303/

They kind of are not though, you can't call them out of order and other things which is checked at runtime by the React "engine" and will stop script execution. If they were regular functions you could call them anytime.

Same here, multiple monitors, overlapping windows has never worked for me. I don't need big monitors for the same reason. I also make sure to keep the number of things I have open to a minimum. Then simply tabbing or using a tiling manager like i3 (without using actual tiling) (they are just faster than running full desktops). It also means I can be productive with any setup anywhere e.g. a laptop

Pretty sure I read Economnics in one lesson because of HN, he makes great arguments about how automation never ruins economies as much as people think. "Chapter 7: The Curse of Machinery"

Regardless of model, I've found LLM's very good at things like Tailwind.

I didn't even want to use Tailwind in my projects, but LLM's would just do it so well I now use it everywhere.

100%

1) Build a directory of X (a gazillion) amount of tools (just functions) that models can invoke with standard pipeline behavior (parallel, recursion, conditions etc)

2) Solve the "too many tools to select from" problem (a search problem), adjacently really understand the intent (linguistics/ToM) of the user or agents request

3) Someone to pay for everything

4) ???

The future is already here in my opinion, the LLM's are good-enough™, it's just the ecosystem needs to catch up. Companies like Zapier or whatever, taken to their logical extreme, connecting any software to any thing (not just sass products), combined with an LLM will be able to do almost anything.

Even better basic tool composition around language will make it's simple replies better too.

I understood it as that the economic relationship they have is going to make Microsoft broke somehow, be it dollars and/or just the focus of the company.

How much did you spend?

Would love more feedback on this, I will definitely downgrade from Max 20x if it is the case. Cost me $350 a month in Australia...