Stop re-explaining your codebase
London, UK
Joined May 2026
- Tweets45
- Following5
- Followers50
- Likes16
Pinned Tweet
The Reverse Information Paradox is real. You don't have to train a model to keep what you learn. Distill the knowledge, not the model.
Satya's diagnosis is right: you pay for intelligence twice, once in cash and once in the knowledge you reveal to use it.
But you don't need training rights to keep it. the learning can stay yours, in token space, today. Here's how: withlore.ai/blog/distill-you…
Planning to bake this into Lore soon. What do you all think?
Ever wondered how did your model affinity/usage changed over time? Well I did and created a tool for you to see yours too. This is mine: modeltides.dev/u/01a0fe78-86…
LoreAI retweeted
Very soon: @withLoreAI - works totally local, fair source, no subscription
Another bit of the new UI just landed: a much better UI to manage contradictory or complementary memory entries
LoreAI retweeted
Dear London friends, I'll be talking about @withLoreAI and its underlying systems a bit tomorrow at @AITinkerers London. Come say hi if you can!
LoreAI retweeted
Amazing to see the ideas behind @withLoreAI being validated by companies like Tencent!
>TencentDB Agent Memory currently supports OpenClaw, Hermes, Claude Code, CodeBuddy, and SDK integration; broader cross-framework migration is on the roadmap.
If you don't want to wait for that, you know what to do 😉
🤯Introducing Team Memory, same idea as Agent Memory, except your teammates' agents can read it too
2.0.0 beta out today, and the repo hit #1 on github's typescript trending this week
Highlights:
> Solo builders: one place to manage memory across all your agents and AI tools, chat, code, tasks. Built for the one-person company
> Teams: a shared memory hub that turns conversations, docs and code into four reusable assets, Chat Memory, Skill, LLM-Wiki, Code-Graph, governed and shared across agents and frameworks
changelog and repo → github.com/TencentCloud/Tenc…
LoreAI retweeted
me before using @withLoreAI
LoreAI retweeted
Now my friend also used Claude for quite a while with Lore and I think this comes close to a poor man's distillation? As in, we captured the best parts of the frontier models and now we can use those with "lesser" models like M2. 7? I have similar feelings for DeepSeek v4 Flash.
Here are the rules Lore runs on. Not aspirations we hope a cooperative model follows: the actual behavior of the layer that touches every token.
withlore.ai/blog/how-lore-re…
The live edge stays whole
The most recent turns are always protected. Whatever gets distilled or dropped as older context is compressed, the active end of the conversation, where the work is actually happening right now, is never touched.