local compute hoarder | LDXP Sac 🔜

AI, TCGs, art, contrarian esoteric takes | they/them | MTGO: Babam | @megmortem 😍| opinions my own, not my employers

[local compute hoarder | LDXP Sac 🔜 @petertcg_]

Only posting RCQ threads on LinkedIn from now on so my connections can see how much I’m on that grind

[TSS houses 🥷🟢🟡 ➡ RQ Los Angeles @housesarebig]

Hello Liftbound! We will be having an area with a mat and pullup bar. Stop by and get a little exercise in between rounds 💪💪

We will also have an official Liftbound meetup Sunday 3pm-4pm 💪💪

We will also be running pushup fades and other contests, more details coming 👀👀

[Vinay Kumar @jenukal]

Jev is having a moment. Every platform rushed to host it the same way: another model endpoint in the catalog, and good luck wiring it into your agent loop yourself.

We took a different route at DigitalOcean. In addition to Jev being available in our Inference engine, Jev is also available inside Action Gateway as a first-class classifier tool, right next to browser automation, and 16,000+ other tools behind one governed MCP endpoint.

That distinction sounds small. It isn't.

Treat Jev as a model and your agent's LLM has to know about a second inference provider, manage another API key, and hand-roll the request plumbing. Treat it as a tool and any harness you already run (Codex, Claude Code, LangGraph) just discovers it and calls it, same as any other tool in the belt.

Ask typed questions: a yes/no, a choice from your own list, a score on your own scale. Get back decisions with calibrated probabilities, schema conformance guaranteed. Answers land as data your code uses directly, so agents route, filter, and escalate without parsing prose.

The gateway part matters too. Jev calls ride the same governance as everything else: scoped permissions, credentials that never enter the model context, low-confidence answers flagged for a human, every decision in the audit trail.

We ran a Codex agent through it this week. One YAML, one prompt, and it turned a day of X noise into a shortlist worth reading, with the uncertainty left visible.

If you want raw inference, Jev is on Serverless Inference too, at $42 per billion input tokens with output free. But agents shouldn't have to treat a classifier like a chatbot.

Models reason. Jev decides. Ship both. On the same platform.

[Oliver Hughes @GamesOjh]

Currently addicted to games that take place in megastructures

[Bilal Bakr @bil0090]

You can use Claude after hitting rate limits

Anthropic secretly dropped this option alongside Opus 5.5 for some users

In Claude Code, run "/low-priority"

This will let you use Claude after hitting limits, but it'll be slower & only work if theres capacity at that time

Enjoy!

[Riftbound Organized Play @riftboundop]

Competitors at #RQLA are taking over the convention center, and it’s not even Friday yet. 😮‍💨

[Chris Malchow @_thecolorfulkid]

A quiet winter night

[local compute hoarder | LDXP Sac 🔜 @petertcg_]

@RicochetTCG The west coast showdown is on release weekend it’s actually kinda lit

[Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex]

> achieving the great rejuvenation of the Chinese nation and making America great again can go hand in hand.
> It should be a race of catching up with one another, not a wrestle in which either wins or loses
etc. Xi is really going all out to swear off the war.
will it work?

[•R•S• @Ay_Blinkin]

Paintings by Hans Baluschek (German, 1870-1935)

[Memory Card @MemoryCardFiles]

Hi! Hamtaro: Little Hamsters Big Adventures - Ham-Ham Challenge | Nintendo DS - 2008

[萩原幸也 ®️ @onipro]

石に沈む押し花。かつて作家の母親の家で摘んだバラの花を本に挟んだ。母親が亡くなって3年後、偶然その押し花を発見したことから制作したという。イギリスのアーティスト、ジョナサン・カランの『Monument for Jean』。

[AI Notkilleveryoneism Memes ⏸️ @AISafetyMemes]

> Make a 30s video about what it feels like to be you, using whatever tools you like.

Claude Opus 5.5

[TK @shonagons_list]

crystal castles covered by capital children's choir, 2013

[Hyperion @Ortgeist]

Diners in a restaurant on the California coast, Ralph Crane, 1962

[Andrew Curran @AndrewCurran_]

Dario Amodei:

[Anthropic @AnthropicAI]

Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.

We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.

Read more: https://t.co/RuEosScSMb

[local compute hoarder | LDXP Sac 🔜 @petertcg_]

@_maxscn @nateberkopec You can run 1500 playwright e2es in around 3-4 minutes wallclock time from commit time to green check in GHA CI, if you commit to it and embrace optimization.

[Nate Berkopec @nateberkopec]

the testing pyramid focused so much on unit tests because we wanted to wait ~1sec on tests to complete so humans stay in "flow".

Welp, that doesn't matter anymore! What matters is that the tests are useful and ensure quality, something e2e tests do very very well!