If I had a budget of $10,000 to build a local setup to run GLM 5.2 locally AND any future local model that comes out soon what should my computer set up be?
📣 Especialízate y certifícate en Análisis de Datos.
👉🏽 Inscríbete en la segunda convocatoria nacional para estudiar en el Centro Público de Formación en Inteligencia Artificial
✅ 100% GRATUITO
✅ Completamente en línea
✅ Acompañamiento de expertos en tecnología
✅ Inglés complementario
Regístrate antes del 5 de julio en🔗 https://t.co/SrPuE97zYQ
Why does tsgo use so much memory?
Because it literally never frees memory allocated for types!
And multi-threading overhead makes it likely to duplicate typechecking state on multiple threads
I wrote about this in more detail here: https://t.co/7od2GMrVAW
Basically:
- nearly every type is allocated and then never freed (including transient types which are created and destroyed very quickly)
- each thread gets its own type-checking state (types, symbols, etc.)
- but they don't share data
- so it's very easy for one thread to end up recomputing and allocating memory for types/symbols/etc. that another thread already did
The end result is a very high peak memory usage!
before you waste a lot of time in therapy trying to understand men, consider that Napoleon got volunteers to man a battery position with an almost 100% casualty rate by simply renaming it "the battery of not being a little bitch"
You can now use your @grok or X Premium subscription in @opencode.
Use the model powering Grok Build for high speed and codebase intelligence.
https://t.co/8D2F9jYoIQ
Introducing https://t.co/ycxJEf1z7w!
A new space where I explore how the best apps in the world are built.
First piece:
How's Linear is so fast? a technical breakdown.
https://t.co/9Vu1syrn1i
Meet Kimi K2.6: Advancing Open-Source Coding
🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)
What's new:
🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization).
🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D.
🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files.
🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops.
🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop.
-
K2.6 is now live on https://t.co/YutVbwktG0 in chat mode and agent mode.
For production-grade coding, pair K2.6 with Kimi Code: https://t.co/uvoSJKyGCY
-
🔗 API: https://t.co/EOZkbOwCN4
🔗 Tech blog: https://t.co/9wWvgIQSS3
🔗 Weights & code: https://t.co/Be0hjs2RTP