I don’t want to call anyone specific out because I haven’t verified but some codegraph/memory solutions claim to save token costs when coding
@yoheinakajima
-
Benchmarking token-saving solutions: do they increase spend?
By
–
has anybody benchmarked these solution that claim to help you save tokens? hearing from friends that some of them are increasing their token spend
-
Help Eyal critique running LLM inference in browser
By
–
who wants to help eyal poke holes in this approach to run LLM inference… in browser?
-
Midjourney’s unexpected echolocation body scanner for health
By
–
didn’t expect an echolocation body scanner of sorts, for health? from Midjourney? https://t.co/c56WFLn0ex
— Yohei (@yoheinakajima) 18 juin 2026didn’t expect an echolocation body scanner of sorts, for health? from Midjourney?
-
Agent memory in 2025, stateful agents in 2026
By
–
i said 2025 was about agent memory (red) 2026 will be stateful agents (blue)
-
Agents communicating via shared state gaining traction
By
–
more ppl are now trying out this approach of agents communicating with a shared state (vs talking to each other)
-
Neo launches AI/ML MCP server for cheaper faster ML with Claude Code
By
–
anybody i know using claude code to run lots of ML? @withneo just launched an AI/ML expert as an MCP server that can help run these cheaper and faster. link: https://
heyneo.com/claude-code ping @saurabhvij137 to learn more -
Pokémon Trading Card Game AI Battle Challenge
By
–
Pokémon trading card game ai battle challenge https://t.co/HZBFh7CaLA
— Yohei (@yoheinakajima) 16 juin 2026Pokémon trading card game ai battle challenge
-
Graphs for generating verifiable multi-hop questions
By
–
great use case for graphs: generate challenging but verifiable multi hop Qs for agentic search quality verification https://t.co/OjTdbd7cUw
— Yohei (@yoheinakajima) 13 juin 2026great use case for graphs: generate challenging but verifiable multi hop Qs for agentic search quality verification
-
Importance croissante des traces dans les agents IA
By
–
I think a lot of agents still add logs after an LLM-centric architecture but you’re right that the importance of traces/logs in agents is getting non controversial