Tony

Agents@zoominfo | Ex-Google Researcher | Coffee&Code Philadelphia Founder

[Tony @pysolver33]

And that's why I am not an entrepreneur but an Engineer!

[Tony @pysolver33]

I hate it when "Founders" sell combustion engines as cows because some VC or Business guy said so.... If the VC or Business guy was good at what they did, they would have sold millions in revenue WITHOUT a product! There is no "correct" "logic" or "thinking" in business!

[Tony @pysolver33]

It's just gaslighting peeps into handing you money! It blows my mind how peeps think there is a "correct" way to do business! I'm not into the business of gaslighting! Peeps has been making trillions of dollars just on top of excel alone. It's not that complicated!

[rahul @rahulgs]

1. as a mental model it is more correct to think of fable+ class models as english -> code interpreters - converts your idea into code into "correct" code regardless of problem complexity and output complexity (diff size). Fable 5 will be the worst of this new class of models

2. diff size/complexity is to be managed purely for review:
small diffs - in high risk areas of code (auth/identity/data access/network access/money movement)
large diffs for code that can be empirically verified (frontend/backend plumbing/code without network or db access/performance code that can be empirically verified)

3. time it takes to ship software is completely disconnected from time to produce the PR - how long the work takes depends fully on ability to review/merge code while managing risk at scale

4. solving the bottlenecks for above matter enormously- linters/testing/CI/shadow mode verification/empirical verification

5. agency matters enormously- what are the biggest bottlenecks to speeding up the loop and eliminating them? what are the problems that need solving and when do they need solving? what does it take to the solution to all of them today?

6. deep understanding of the full stack matters enormously- what problems are worth pursuing? is there a higher level of problem abstraction to address first? should I give it the sub-sub task, the sub task, or the task itself. what are the major risks with this PR (order of importance: security holes/correctness holes/performance holes). is there a higher speed way of producing data that allows me to merge this? should this be run in shadow or in a sandbox or a flag. understanding every line of logic may not be needed but understanding and managing risk matters enormously.

7. the cost of complexity itself is changing. it might be now worth "maintaining" 50% more code to get a 5% performance win. getting the right abstractions matter less because larger refactors are less tedious. code quality nits become huge drag. very likely, a much smarter model will be maintaining your code so worth taking on more technical debt now. taking the time to hand architect and rebuild systems comes with an enormous cost of velocity

8. if it quacks like a duck and walks like a duck, it's a duck. For low risk cases, it might be more sane to treat code chunks (services / functions) as a black box, like we do for neural networks: do full empirical verification only: has code produced correct outputs for the last 10,100,1000,10k inputs ? can we quarantine this large piece of code - no outbound access to network / database ? what happens when this code is wrong? do we get hacked/or crash(memory/cpu)/is an inconvenience? is it internal facing or external? what can we do to address these risks?

9. eventually, logical verification (line by line review) will come at an enormous cost- save it for where it matters and build systems that are tolerant to empirical verification. is there a decorator that prevents db / network access? correctness bugs are significantly easier to rectify than access bugs

10. what are the rails that allow for even faster iteration? code permissions can be opt in - db writes, db reads, network egress (to where?), PII access. how long does it take to get shadow mode data? how many PRs can be tested? What are the categories of diffs

[Chris Tate @ctatedev]

☰╱☰

The framework for building agents

Build a company brain, personal assistant, or domain-specific agent

→ Data
→ Evals
→ Tools
→ Skills
→ Schedules
→ Subagents
→ Durable workflows
→ Sandboxed execution
→ Connections (services/MCP)
→ Channels (Slack/web/Discord)

[Nolan Makatche @NolanMakatche]

That's a wrap on another Coffee & Code at Pennovation Works, and wow, what a room! @PennovationWork

Founders, devs, designers, and researchers all heads-down side by side, building everything from biotech to AI. The energy was unmatched.

Huge thank you to Composio and Pennovation Works for hosting us inside Philly's most interdisciplinary innovation hub. 🙌 @composio

And to everyone who showed up, opened a laptop, and built alongside strangers who became collaborators by lunch.

You're the reason this community keeps growing. ❤️

Why Composio? Connecting AI agents to real tools like Gmail, Slack, GitHub, and 250+ apps usually means wrangling a different auth flow and API quirk for every single one. Composio solves that with one unified integration layer, so your agent can actually do things across all your apps without you hand-rolling and babysitting each connection.

Already missing it? We're back in July!
Composio Founder Build Day, Friday, July 17 · 10 AM
Pennovation Center, Philadelphia

Bring your laptop. Bring your project. Bring a friend. Let's build. ⚡️

Shout out to @pysolver33, @The_Only_Signal, @chrislikewater @OlehSavcuk and many more for joining us!

[Tom Dörr @tom_doerr]

Generates software architecture diagrams from code

https://t.co/EduXXEAgUo

[Tony @pysolver33]

@derekmeegan Holy shit was what caught my attention

[Tony @pysolver33]

@derekmeegan haaa

[Mike Bradley @The_Only_Signal]

It would genuinely be hilarious if Dario’s fear mongering power grab is exactly what kills his IPO. Seized as a national resource because he shouted “too dangerous to release” too many times and Washington actually believed him.

[Anthropic @AnthropicAI]

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.

The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.

Access to all other Claude models is not affected.

We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.

Read our full statement: https://t.co/bwn0sximKZ

[Ahmad @TheAhmadOsman]

https://t.co/riIctxjHoN

[Tom Dörr @tom_doerr]

Obsidian vault for AI agent memory

https://t.co/sdrDs7mJiE

[alphaXiv @askalphaxiv]

As believers of open research, we are disappointed to see Anthropic silently degrading Fable 5 for AI development

"Any topic related to building pretraining pipelines, distributed training infrastructure, or ML accelerator design... may have limited effectiveness through Claude via methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning."

Not only do they get to decide what you use LLMs for in research, but this also enables them to silently intervene in your research without you knowing.

This sets a dangerous precedent. If a model refuses openly, users can understand the boundary. If a model falls back to another model, users can still evaluate the difference. But if a model silently modifies or weakens its own answers while still pretending to help, researchers lose the ability to know whether a failed result came from their own idea, their implementation, or an invisible intervention by the model provider.

That is not safety. Safety policies should be transparent, auditable, and user-visible.

On top of that, the people most harmed by this are not the largest labs with massive teams and proprietary infrastructure. It is the independent researchers, academic groups, startups, and open-source builders who rely on public tools to compete, innovate, and pioneer AI for everyone else.

[Tony @pysolver33]

The Long Way Home — How Tony Siu Went from Exchange Student to AI Engineer to Philadelphia’s Community Builder
https://t.co/x5tj0WiiUy

[elie @eliebakouch]

mythos will be bad ON PURPOSE on ai "frontier llm research" tasks, this is very very sad for the research community

also the fact that this is un purpose not visible to the user is crazy

[Ethan Mollick @emollick]

The fact that Anthropic may take away subscription access to Fable in two weeks is weird & discourages investing in learning about the model.

Subscription use is how you figure out what the model is good for, since it allows experimentation. Only having paid access is limiting.

[Mike Bradley @The_Only_Signal]

Hard agree.

[Mike Bradley @The_Only_Signal]

Even if Mythos wasn’t hype relative to GPT-5.5, I think the whole dog and pony show was they just didn’t have the compute to serve it at scale.

I still think that’s the issue which is why they are pre nerfing it. It’s not a matter of “too dangerous to release” it’s simply “too compute thirsty to serve”. Same thing happened with 4.6.

They can make good models but they can’t host them at full quality at the same scale as their demand, so in comes weird usage limit revisions, use case restrictions, and nerfs.