Tyler Casey

Builder @Swarm_Signal /@bored_tools

[Tyler Casey @getboski]

Two goals in a minute! Come on England

[Tyler Casey @getboski]

@coreyhainesco I’ve installed this (previous version) for high level marketers + their team (VP level) who are finding it very useful, so thanks for the work you put into building it

[Tyler Casey @getboski]

@Cloudflare Joined the waitlist!

[Tyler Casey @getboski]

@tunguz Size of those sd cards

[Tyler Casey @getboski]

@astuyve Also - I ran the same benchmark audit of my agentOS setup today with DSeek + GLM + GPT 5.5 extra high, and the resulting best to worst results were GLM 4.2 -> Deepseek v4 pro -> GPT 5.5

[Tyler Casey @getboski]

@astuyve Yes, I started out with deepseek and glm in opencode but someone mentioned zcode and I moved to using both within that harness after trying it out, it is very good

[Tyler Casey @getboski]

@GammaVibe @nia_thinks Came here to say the exact same thing!

[Tyler Casey @getboski]

I made the switch about a month ago - no regrets

[Tyler Casey @getboski]

The temptation to switch from Claude max to open ai pro is real

[Tyler Casey @getboski]

I think one of the unexpected joys of AI is that you never really “finish” your setup.

You just keep refining it with one workflow, one prompt, one agent at a time.

What a time to be alive.

[Tyler Casey @getboski]

GLM 5.2 as an auditor is fire. I’m still reaping the benefits of an annual coding life plan for $34 I purchased some time ago

Find the bugs
Fix the bugs
Ship

[Reed @reed_barnes]

it's 2027. you take a free-tier public Waymo to the DMV (Department of Model Variance) to do a proof-of-identity check for access to GPT 7.1.

the guy at the counter is clearly watching a Mr. Beast video in his AR glasses. "Here for that new model?" he says, barely making eye contact. he wipes his fingers on his shirt and taps at his keyboard. "Lot of you techies showing up here today." you smile politely; you're pretty sure he's just a Claude wrapper anyway.

you lean forward and stare into the retinal scanner. after a long moment, there's a soft chime. "Humanity confirmed. U.S. national. Intelligence access: Terra-class."

you sigh with quiet relief as your devices light up—notifications from a hundred agents, finally able to resume their tasks. you feel a twinge of guilt as you terminate your open-weight backup agents, but remind yourself that a joint congressional committee proved conclusively that Chinese models are non-ensouled.

you step outside and hail another Waymo. the first one passes you by. you grimace; must've burped in that one once. stupid personalized memory.

as you're waiting, your phone buzzes angrily, red notifications blaring across the screen. the Department of War just restricted access to all OpenAI models on serious national security concerns; apparently Pete Hegseth got GPT-6-Instant to say "Claude is a woman." you groan, and resign yourself to another week of merely-somewhat-superhuman intelligence.

Fable 5 is still inaccessible to the public. a twitter anon you trust says it's coming back this week. or maybe next.

[Roy @usr_bin_roygbiv]

5.5 is smart enough to cram everything into a single agents.md file with all your repos in a single workspace.

Containerize and break everything into microservices with TDD for everything with its own repo and pipeline. Put docs in html in their own repo and enforce it in HTML with hyperlinks so you can read them as well easily.

By splitting out the services more you can have agents recursively spawning subagents by devloop and splitting out work as effectively as needed on worktrees or patches in each repo. I use apfs/git worktrees are setup by default in omp for subagents. 5.5 is smart enough to know exactly how many subagents it needs and what depth the agent tree should go with recursion turned on.

You can refactor, rewrite, test, deploy your entire codebase with a single prompt. I'm currently managing a ~6m line codebase this way and self hosting everything. All infra code has its own repo for helm/csps. Metrics and tests on all services and grafana dashboards for tracking everything. Every stat I can possibly think of or ever will need gets shoved into postgres.

Any heavy data work or code that needs to be written gets metrics assigned to it in prom or pg and then gets targeted for /goal or for /autoresearch for optimization. I typically explore everything with gemini and have it write the prompts to hand off to 5.5.

People are simply not pushing the models hard enough. 5.4 and 5.5 (maybe even kimi and ds) ARE ASI. The bottleneck is yourself, compute, and devloop times.

[Tyler Casey @getboski]

@Yerbamatt Well done mate!

[Tyler Casey @getboski]

I built a super-audit skill in @deepseek_ai for reviewing codebases and catching issues that even Codex can miss.
It’s token-intensive, but DeepSeek makes that far less painful - and early results have been strong.
I’ll push it to GitHub after further testing today.

[Tyler Casey @getboski]

@Carl_Cox DJ Set @ Ultra 2018: Resistance Megastructure - Day 1 (https://t.co/PISFfpAgx7) https://t.co/Mu9g01KN4M via @YouTube OH YES OH YES

[Tyler Casey @getboski]

I switched ZCODE over to DeepSeek - or DSeek, as it’s apparently known in the UK now - and haven’t looked back. It’s rapid, the output is excellent, and the price still feels slightly made up.

[Tyler Casey @getboski]

I asked GPT-5.5 Pro to reimagine Douglas Adams’ Shoe Event Horizon for the age of chips, agents and endless compute.

The result: The Compute Event Horizon.

A joke, obviously.

Mostly.
https://t.co/B6kpgZF18V

[Alperen @Nereplan]

@dedene Reminds me of this lmao

[Tyler Casey @getboski]

@chris_bgp ✋