anthonyagnone

Machine Learning | Software | Music

[Gergely Orosz @GergelyOrosz]

So many vendors are NOT getting this

I have one or two agents I use and like. For anyone else: give me an MCP interface to connect these agents to so I can use your service

Unless your a frontier AI lab, I prob don't want to use your agent, sorry

[anthonyagnone @anthonyagnone]

@grok analyze a high-level system design for this.

Communication: Buzz
Source code: Buzz
Proj mgmt: Multica vs Linear vs <bespoke>
Agent harnesses: Claude/Codex/Cursor/Pi/Hermes

include cron jobs, event-driven agent work from the proj mgmt system, master agent orchestrator

[anthonyagnone @anthonyagnone]

Rebase this on Buzz and add kanban proj mgmt in there. Then builders have all of this under one hood without vendor lock-in or dumb rate limits:
- Team comms
- Source code mgmt
- Proj mgmt
- Agent harness flexibility

Best part: less assumptions than the skill soup being pushed

[Garry Tan @garrytan]

Your personal AI or your company brain needs a clean harness and this is the one our team built and uses every day

Free and open source

[Chamath Palihapitiya @chamath]

Here is my AI investing guide.

Sitting here August 2026, my current best thoughts are as follows:

1. LPS (Land Power Shell) is still the most obvious and fastest path to cash on cash returns. Lots of value can be assembled and traded quickly at this layer. And as data centers get more pushback, energized land can explode in value. Very bullish here.

I’ve stepped into this layer very aggressively. My partner @anitavlallian and I have acquired almost 6GW coming online in a ramp from today thru 2029 of grid power and behind the meter.

2. Silicon - I helped get @GroqInc off the ground in 2015 and we licensed it to @nvidia for $20B Dec2025. I won’t invest or incubate anything in this layer now. The perf demands of the chips are too high, manufacturing precision is too complex and supply chain influence to get adjacent components like memory isn’t possible for a startup anymore. Lots of capital will be wasted here chasing Groq and Cerebras’ success. Note that both startups made sense a decade ago when these constraints were much more modest.

3. Clouds - Clouds are very very lucrative but very hard to build and very expensive and technically complicated to maintain. And as alignment becomes a more important issue, I expect the clouds will be asked to build robust KYC and attest to it. This makes the risk:reward ratio skewed. I don’t want to be responsible when the USG says a cloud allowed a bad actor to do something bad because of poor KYC.

4. Models are complicated. The big open question is how much of the revenue being generated by them today is because of tokenmaxxing and poor model behavior. If it’s a lot, then the annualized revenues will diminish meaningfully even as token consumption inflects upwards. This is the big economic question at this layer.

5. Harnesses are where the action is and why I started @8090solutions two years ago. In a nutshell, the harness helps enterprises owns their proprietary context (what Alex Karp calls their ‘alpha’). This is an enterprise’s data, workflows, evals, and business rules. A harness that gives this to an enterprise is what creates very low model-agnostic switching costs, which further reinforces my views of #4 above.

6. Applications will be another long term winner along with harnesses. This is where the differentiation between “off the shelf” and “custom time and materials” melts away. Every company, with the right harness, can now imbue their alpha into the software that runs their company. I expect this to mean that “off the shelf” is largely replaced with custom software creating a huge opportunity to write these solutions for companies. Build once and sell repeatedly is a laggard GTM motion for a SaaS world that isn’t needed here. Think custom by design, alpha embedded, proprietary by nature.

Fin.

Good luck to all the players!

[anthonyagnone @anthonyagnone]

https://t.co/Nu4EZNq4b4

[anthonyagnone @anthonyagnone]

Web scraping can be abused. We still don’t ban the tool.

Site owners defend their systems. The law targets fraud and theft.

AI distillation deserves the same careful line.

[anthonyagnone @anthonyagnone]

@imcharliegraham I guess Opus 5 insists on making mistakes 🤘🤪

[anthonyagnone @anthonyagnone]

I'm not quite there yet but I 100% agree with the sentiment. There's still time for course correction 🤞🏼

[Santiago @svpino]

My transition away from Anthropic is now complete.

I love their models. I love Claude Code. But I'm not willing to keep sending them money while they keep lobbying the government to stifle competitors.

I hope Anthropic finds its way, and I'd be happy to consider them again when they do.

[anthonyagnone @anthonyagnone]

I think the most **load-bearing** thing that @claudeai can do right now is evaluate how it talks with TF-IDF...unless that's too old school and we should eschew statistics and prompt the bejesus out of it with "no AI slop" skills

[anthonyagnone @anthonyagnone]

I’m talking with Opus 5 about the open weights regulation debate and it’s very interesting seeing it decline certain conversation topics 👀

[anthonyagnone @anthonyagnone]

Immediately sniped by @claudeai 😅

[anthonyagnone @anthonyagnone]

My AirPod wasn’t connected to my phone when I did a transcription and this is what it registered 😐🇳🇴

[anthonyagnone @anthonyagnone]

@AlfieJCarter COWORK

[anthonyagnone @anthonyagnone]

@rom1trs Motion

[anthonyagnone @anthonyagnone]

@LoganTGott PROMPTS

[anthonyagnone @anthonyagnone]

“Loop engineering” is just software engineering…

- Process design
- Event-driven architecture
- Systems thinking
- Debugging

It feels different since AI has made leaps and bounds on what the computer can do without needing the human.

But take a 50ft view of it, helps a lot

[anthonyagnone @anthonyagnone]

@Jacobsklug NATIVE

[anthonyagnone @anthonyagnone]

@AlfieJCarter Skills

[anthonyagnone @anthonyagnone]

@AlfieJCarter Agents

[anthonyagnone @anthonyagnone]

@garrytan How ridiculous!! You should be on the beach on Claude Code 😁