ai coding is getting expensive use more open models!
LLMS
-
SkillOS: Skill Curation for Self-Evolving Agents
By
–
SkillOS Learning Skill Curation for Self-Evolving Agents paper: https://
huggingface.co/papers/2605.06
614
… -
Apple introduces TIDE: Every Layer Knows the Token Beneath the Context
By
–
Apple presents TIDE Every Layer Knows the Token Beneath the Context paper: https://
huggingface.co/papers/2605.06
216
… -
LLMs’ Math Progress Accelerates Rapidly
By
–
It's surprising to see the pace of progress of LLMs (which until not long ago were very bad at math) achieving ever greater milestones. Take a look at the graph above. The progress curve is getting faster and faster. I'll leave the link to the paper here: https://
arxiv.org/abs/2605.06651 -
Google reclaims lead in FrontierMath Tier 4
By
–
LEADER in FRONTIER MATH T4! New record in one of the most challenging math benchmarks -FrontierMath Tier 4- where Google has just reclaimed the lead with a 47.9% !!, stealing the position from GPT 5.5 Pro It does it with its new math agent
-
New Continuous Latent Diffusion Language Model paper
By
–
Continuous Latent Diffusion Language Model paper: https://
huggingface.co/papers/2605.06
548
… -
Global Activation Approximation for Long-Context Understanding
By
–
MiA-Signature Approximating Global Activation for Long-Context Understanding paper:
https://huggingface.co/papers/2605.06416
… -
OpenAI improves remote control of Codex
By
–
OpenAI continues working on Remote Control for Codex, which will allow it to manage remote instances via SSH. A new toggle has been added to the settings that will keep remote connections open. Someone will definitely ask Codex to fix bugs on production at some point 😛
-
AI tokens wasted on shell command outputs, not code
By
–
90% of the tokens your AI burns aren't from your code.
— AlphaSignal AI (@AlphaSignalAI) 8 mai 2026
Every shell command your agent runs returns raw output.
`git status`, `find`, and `ls` are all read by the LLM in every single run.
A single `playwright test` run dumped enough output to consume 8,100 tokens.
Two… pic.twitter.com/yX1u9lcBo290% of the tokens your AI burns aren't from your code. Every shell command your agent runs returns raw output. `git status`, `find`, and `ls` are all read by the LLM in every single run. A single `playwright test` run dumped enough output to consume 8,100 tokens. Two
-
Using Claude as a personal multimedia system with custom prompts
By
–
J’ai arrêté de payer Spotify. Résilié Netflix. Résilié Disney+. Maintenant, mon laptop est devenu un meilleur centre de divertissement…gratuitement. Grâce à Claude. Voici 8 prompts qui ont transformé l’IA en système multimédia personnel : [ Ajoutez en signet pour ne pas