Between scant repo examples, FastMCP's irritating vector resemblance to FastAPI, and 180 degree overhauls on every MCP spec release, it's impossible to vibe code your way to a working server.
October 13, 2025 at 11:05 PM
Between scant repo examples, FastMCP's irritating vector resemblance to FastAPI, and 180 degree overhauls on every MCP spec release, it's impossible to vibe code your way to a working server.
Hiring for engineers? Instead of a leetcode interview, try asking them to build an #MCP server in Python.
This first turn on Claude Opus 4.1 is so wrong it might just take burning the rest of humanity's natural gas reserves to fix it.
This first turn on Claude Opus 4.1 is so wrong it might just take burning the rest of humanity's natural gas reserves to fix it.
October 13, 2025 at 11:05 PM
Hiring for engineers? Instead of a leetcode interview, try asking them to build an #MCP server in Python.
This first turn on Claude Opus 4.1 is so wrong it might just take burning the rest of humanity's natural gas reserves to fix it.
This first turn on Claude Opus 4.1 is so wrong it might just take burning the rest of humanity's natural gas reserves to fix it.
The solution is to reinforce the use of knowledge tool calls for every query in post-training. By consistently grounding responses to citable sources, even the occasional quirk and hallucination are explainable.
October 9, 2025 at 1:56 AM
The solution is to reinforce the use of knowledge tool calls for every query in post-training. By consistently grounding responses to citable sources, even the occasional quirk and hallucination are explainable.
This phenomenon can sneak into production environments in unobvious ways. If there are enough token predictions pointing to the right answer, it's all too easy to skip the tool call and generate a structured response that still validates schemas.
October 9, 2025 at 1:56 AM
This phenomenon can sneak into production environments in unobvious ways. If there are enough token predictions pointing to the right answer, it's all too easy to skip the tool call and generate a structured response that still validates schemas.
It's fascinating to see the Mandela Effect take hold on LLMs as much as it does people.
This is especially true for LLMs that see its own pretrained memory as a tool for knowledge recall, rather than as an orchestrator (most LLMs).
This is especially true for LLMs that see its own pretrained memory as a tool for knowledge recall, rather than as an orchestrator (most LLMs).
October 9, 2025 at 1:56 AM
It's fascinating to see the Mandela Effect take hold on LLMs as much as it does people.
This is especially true for LLMs that see its own pretrained memory as a tool for knowledge recall, rather than as an orchestrator (most LLMs).
This is especially true for LLMs that see its own pretrained memory as a tool for knowledge recall, rather than as an orchestrator (most LLMs).
89,886 developers are building their own Perplexity on-prem with Diffbot LLM —
huggingface.co/diffbot/Llam...
huggingface.co/diffbot/Llam...
diffbot/Llama-3.1-Diffbot-Small-2412 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 30, 2025 at 3:08 AM
89,886 developers are building their own Perplexity on-prem with Diffbot LLM —
huggingface.co/diffbot/Llam...
huggingface.co/diffbot/Llam...
The model isn't the moat. Perplexity can be recreated as a side project. #DeepSeek proved this. We proved this.
Download Diffbot LLM. Run it off your own GPU. Congrats, your on-prem #AI is smarter than #Perplexity.
Download Diffbot LLM. Run it off your own GPU. Congrats, your on-prem #AI is smarter than #Perplexity.
January 30, 2025 at 3:08 AM
The model isn't the moat. Perplexity can be recreated as a side project. #DeepSeek proved this. We proved this.
Download Diffbot LLM. Run it off your own GPU. Congrats, your on-prem #AI is smarter than #Perplexity.
Download Diffbot LLM. Run it off your own GPU. Congrats, your on-prem #AI is smarter than #Perplexity.
2. We used the profits from our primary business to train Diffbot LLM. Perplexity raised $915M to train theirs.
3. We open sourced Diffbot LLM. Perplexity chose to keep theirs secret.
3. We open sourced Diffbot LLM. Perplexity chose to keep theirs secret.
January 30, 2025 at 3:08 AM
2. We used the profits from our primary business to train Diffbot LLM. Perplexity raised $915M to train theirs.
3. We open sourced Diffbot LLM. Perplexity chose to keep theirs secret.
3. We open sourced Diffbot LLM. Perplexity chose to keep theirs secret.
Let's be frank — The score difference is insignificant. And we'll probably play SimpleQA tag for awhile.
What IS significant is how we got here vs. Perplexity.
1. Diffbot LLM is a side project. Sonar is Perplexity's entire business.
What IS significant is how we got here vs. Perplexity.
1. Diffbot LLM is a side project. Sonar is Perplexity's entire business.
January 30, 2025 at 3:08 AM
Let's be frank — The score difference is insignificant. And we'll probably play SimpleQA tag for awhile.
What IS significant is how we got here vs. Perplexity.
1. Diffbot LLM is a side project. Sonar is Perplexity's entire business.
What IS significant is how we got here vs. Perplexity.
1. Diffbot LLM is a side project. Sonar is Perplexity's entire business.
...so I set it up to run the 4000 question eval on Diffbot LLM overnight and went to bed.
The next morning, we beat Sonar Pro.
The next morning, we beat Sonar Pro.
January 30, 2025 at 3:08 AM
...so I set it up to run the 4000 question eval on Diffbot LLM overnight and went to bed.
The next morning, we beat Sonar Pro.
The next morning, we beat Sonar Pro.
While working on my talk last week, Perplexity released Sonar Pro API with a special emphasis on its factuality benchmark F1 score of 0.858, handily beating other internet connected LLMs like Gemini-2.0-flash.
The SimpleQA benchmark they used is open source and LLM judged...
The SimpleQA benchmark they used is open source and LLM judged...
January 30, 2025 at 3:08 AM
While working on my talk last week, Perplexity released Sonar Pro API with a special emphasis on its factuality benchmark F1 score of 0.858, handily beating other internet connected LLMs like Gemini-2.0-flash.
The SimpleQA benchmark they used is open source and LLM judged...
The SimpleQA benchmark they used is open source and LLM judged...
#Perplexity Sonar Pro API launched last week as the best performing model on factuality.
24 hours later, it's the 2nd best performing model (and it's not because of #DeepSeek).
Why? 👇
24 hours later, it's the 2nd best performing model (and it's not because of #DeepSeek).
Why? 👇
January 30, 2025 at 3:08 AM
#Perplexity Sonar Pro API launched last week as the best performing model on factuality.
24 hours later, it's the 2nd best performing model (and it's not because of #DeepSeek).
Why? 👇
24 hours later, it's the 2nd best performing model (and it's not because of #DeepSeek).
Why? 👇
A demo is also available at diffy.chat.
We look forward to building a future of grounded AI with you all.
We look forward to building a future of grounded AI with you all.
Diffy Chat
diffy.chat
January 9, 2025 at 9:47 PM
A demo is also available at diffy.chat.
We look forward to building a future of grounded AI with you all.
We look forward to building a future of grounded AI with you all.
Diffbot LLM's lighter footprint puts on-prem hosting well within reach.
And we are excited to share that we are releasing Diffbot LLM open source on #Github, with weights available for download on #Huggingface.
github.com/diffbot/diff...
And we are excited to share that we are releasing Diffbot LLM open source on #Github, with weights available for download on #Huggingface.
github.com/diffbot/diff...
GitHub - diffbot/diffbot-llm-inference: DIffbot LLM Inference Server
DIffbot LLM Inference Server. Contribute to diffbot/diffbot-llm-inference development by creating an account on GitHub.
github.com
January 9, 2025 at 9:47 PM
Diffbot LLM's lighter footprint puts on-prem hosting well within reach.
And we are excited to share that we are releasing Diffbot LLM open source on #Github, with weights available for download on #Huggingface.
github.com/diffbot/diff...
And we are excited to share that we are releasing Diffbot LLM open source on #Github, with weights available for download on #Huggingface.
github.com/diffbot/diff...
At Diffbot, we believe that general purpose reasoning will eventually be distilled down to ~1B parameters.
Knowledge is best retrieved at inference, outside of model weights.
Knowledge is best retrieved at inference, outside of model weights.
January 9, 2025 at 9:47 PM
At Diffbot, we believe that general purpose reasoning will eventually be distilled down to ~1B parameters.
Knowledge is best retrieved at inference, outside of model weights.
Knowledge is best retrieved at inference, outside of model weights.
The benefit of full source attribution goes two ways.
Not only is credit provided to publishers, every fact is also independently verifiable.
Not only is credit provided to publishers, every fact is also independently verifiable.
January 9, 2025 at 9:47 PM
The benefit of full source attribution goes two ways.
Not only is credit provided to publishers, every fact is also independently verifiable.
Not only is credit provided to publishers, every fact is also independently verifiable.
Every response from Diffbot LLM draws from the results of real-time expert web searching and queries to the Diffbot Knowledge Graph.
Naturally, this means Diffbot LLM always provides full attribution to its cited sources.
Naturally, this means Diffbot LLM always provides full attribution to its cited sources.
January 9, 2025 at 9:47 PM
Every response from Diffbot LLM draws from the results of real-time expert web searching and queries to the Diffbot Knowledge Graph.
Naturally, this means Diffbot LLM always provides full attribution to its cited sources.
Naturally, this means Diffbot LLM always provides full attribution to its cited sources.