TDG

Experience designer, filmmaker,photographer,time-traveller, writer, dreamer, argumentative Indian,

[Demis Hassabis @demishassabis]

https://t.co/PTeDiv1b6L

[Satya Nadella @satyanadella]

https://t.co/xv6csf1SbV

[BridgeMind @bridgemindai]

FABLE 5 CAME BACK NERFED.

We re-ran the July 1st version of Claude Fable 5 on BridgeBench.

The results are brutal:

Debugging: 86.2 → 25.9
Refactoring: 73.6 → 38.4
Hallucination: 75.9 → 61.7

The new guardrails are kicking in on way too many tasks and falling back to Opus 4.8.

This is not the model that got banned.

Anthropic owes everyone an explanation.

[Thariq @trq212]

https://t.co/R6exTuF7P8

[BuBBliK @k1rallik]

🚨 do you understand what happened to Claude..

Anthropic just shipped Opus 4.8 with something called dynamic workflows.

It no longer works alone - it spins up hundreds of agents that argue, verify, and break each other's work until the answer is right.

- A dev used it to port Bun from Zig to Rust in 11 days
- 750,000 lines of Rust, 99.8 percent of tests passing
- Hundreds of agents ran in parallel with two reviewers per file
- Fast mode runs the same model 2.5x faster and 3x cheaper than before

work you used to plan in quarters now finishes before the weekend

[Thariq @trq212]

https://t.co/MXt5XS4xBX

[ClaudeDevs @ClaudeDevs]

Usage limits are up, effective today we're:

1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans

2) Removing peak hours limit reduction on Claude Code for Pro and Max plans

3) Substantially raising our API rate limits for Opus models

[TDG @tirtho1712]

@cyrilXBT Claude

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

[TDG @tirtho1712]

@HalimA60962 Gemini

[TDG @tirtho1712]

@InduTripat82427 LLM

[Indu Tripathi @InduTripat82427]

This is insane 😳
Most people are just using AI tools
Very few actually understand how they work

So I collected Stanford’s complete LLM curriculum
and turned it into a step-by-step learning path

Worth over $500
Giving it away free for the first 4,500 people

Transformers → Training → Alignment → Agents → Evaluation

Study this once and you’ll stop guessing with prompts
and start thinking like a real AI engineer

How to get it:
Follow must (so i can dm you)
Rt and comment 'LLM'

[Rishabh @Rixhabh__]

BREAKING: Grok can now teach you any skill in 30 days for free.

Use these prompts to replace $20,000 courses and 4-year degrees:

[TDG @tirtho1712]

@KrishnanRs2 @hvgoenka Ah! What the Delhi based central politicians did? Who dried the capital flows in Kolkata ?

And which city got a refugee in Crores twice within 25 years ?

[TDG @tirtho1712]

@TheStatesmanLtd When it is going to be released?

[TDG @tirtho1712]

@GeeDee1211 @vikrantgupta73 O hello, What happened to Bengaluru after the IPL? How many people died? Or at New Delhi railway bridge or Tirupati stampede and chaos this year ? Kolkata manages the grand Durga Pruja event every year with lakhs of people visit or Ganga Sagar Mela or International Book Fair.

[TDG @tirtho1712]

@RusGarbageHuman @LozzaFox Every civilisation has its time. None has been eternal. The modern white lineage was also formed after the Roman conquest and later with the Scandinavian tribes and others. It’s same in other parts of the world too. Need to accept.

[Sam Altman @sama]

which one is supposed to be the left-wing propaganda machine again?

[TDG @tirtho1712]

@MichaelVaughan Root is a classical test great like Dravid and more reliable than Kohli in test cricket if you consider the overall career, but in his pick form between 2014-18, Kohli is a better match winner and has the X factor in tough conditions.

[TDG @tirtho1712]

@ravimathur15 @MichaelVaughan I don’t think India these days make good batting pitches for test cricket. It’s always challenging for the batters because of slowness, turning etc.