syntex

work: claude subs Opus 5.5 mostly

personal: $200 for ultra claude subs + I haveT5810 with older xeosn e52499v4 128gb ram + 3060 12gb ram with Strata

I actually use my personal claude 100% every week I could easily do with 2-3 subs more. I would easily find a work for them.

I had a similar experience with Namecheap. Their bot crawled my website while it was still under construction and apparently reported it to some security databases, causing my domain to be flagged as suspicious.

Since then, my domain's reputation has been affected, and I often get security warnings when trying to access my own website through my company's VPN.

Namecheap simply informed me that it had been a mistake, but the damage was already done, and the issue still persists.

Recently, Meta closed my account, along with access to all my Meta Quest games, because I didn't verify my age in time. Because the account is closed, I can’t even contact support. I received a few emails about age verif. but first, I don’t want to provide my ID everywhere, and second, why automatically close an account with all my purchases on it? Why can't you wait until I log in? Super frustrating / terrible company.

Be careful when transposing game-learned behaviors into real life.

yes I always thought it's an easy thing. but I changed my mind recently when I had to deal with it.

A lot little things you need to think of. For example.

Client sends a request. The database is temporarily down. The server catches the exception and records the key status as FAILED. The client retries the request (as they should for a 500 error). The server sees the key exists with status FAILED and returns the error again-forever. Effectively "burned" the key on a transient error.

others like:

- you may have Namespace Collisions for users... (data leaks) - when not using transactions only redis locking you have different set of problem - the client needs to be implmented correctly. Like client sees timout and generates a new key, and exactly once processing is broken - you may have race conditions with resource deletes - using UUID vs keys build from object attributes (different set of issues)

I mean the list can get very long with little details..

You've some wrong assumption. One is that you are wrong about Poland / Greece wages. In 2026 Polish worker actually earns more than a Greece worker for the same role. Something like 25% more in Poland

Also Polands power grid is quite old and hasn't kept pace with demand. The grid operator last year had to reject thousands of requests for new connections

Thanks! I wasn't aware of Jido or ReqLLM before. ReqLLM looks especially promising, and I will likely use it. At the moment, I'm only integrated with OpenRouter.

Its semi public, but I probably publish it soon once its less embarrassing.

Its an Elixir agent runtime with a thin Go TUI (bubble-tea). Im building it mostly to explore agent orchestration: planner/workers/finalizer flows, local file/code-edit tools, MCP tools, permission gates, run context, compaction, and eventually larger swarms. Erlang/Elixir is interesting for this because the actor/supervision model maps pretty naturally to lots of isolated agents and long-running supervised tasks.

As i said, The main lesson so far is that everything around contracts is much more fragile than I expected unless you use a very strong model. Planners return Markdown instead of JSON, tools get called with subtly wrong args, subagents repeat broken tool calls, finalizers lie about success after workers failed. And various permissions may be interpreted by agents in unexpexted way

I also started with too many modes too early instead of making agentic path extremely solid. That made me understand better why these codebases become huge: there are endless corner cases if you want a harness to work across models, providers, tools...

Stronger models hide a lot of harness weakness and weaker models expose. Making weaker models good enough requires a surprising amount of contract hardening. But that hardening tends to make the system better for stronger models too.

Also elixir http stack was causing a lot of problems (needed to use gun eventually)

Not sure you can replace Claude with DeepSeek V4 that easily and have same results.

From what I see while building my own agentic system in Elixir, the problem is in training for your specific harness/contracts. Claude/GPT-style models seem to be trained around very specific contracts used by the harness like tool call formats, planning structure, patching, reading files, recovering from errors, and knowing when to stop.

In practice, you either need a very strong general model that can infer and follow those contracts (expensive), or a weaker model that has been fine-tuned / trained specifically on your own agent contracts. Otherwise, the whole thing becomes flaky very quickly. And I suspect with Deepseek V4 you may get last options.

These benchmarks means very little. The real test is model + harness so agentic system that can fulfill given goals.

hallucinates in pretty much every answer

Yes, I did it as a joke inspired by the PRISM release. But unexpectedly, it makes a good point. And the funny part for was that the paper lists only LLMs as authors.

Also, in a world where AI output is abundant, we humans become the scarce resource the "tools" in the system that provide some connectivity to reality (grounding) for LLM